© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67688
    Prev
    Next
    INDEX
    Explanations

    utility and its applications

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on occurrences of the word “utility” (and its closely related forms, e.g. “utilities”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of “utility” or “utilities,” especially in titles, organization names, technical headings, and discussions of tools or services.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "utility" or "utilities" in formal or technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -2.44
    pecabe
    -2.36
    鬭
    -2.14
    llavero
    -2.13
    kemeja
    -2.11
    絎
    -2.03
    archiwizowane
    -2.00
    侂
    -1.91
    brinco
    -1.90
    呿
    -1.88
    POSITIVE LOGITS
    ]
    2.63
    }
    2.27
    :
    2.11
    The
    2.08
    са
    2.06
    ات
    1.98
    та
    1.95
    <i>
    1.91
     escrito
    1.91
    ”
    1.85
    Activations Density 0.017%

    No Known Activations