© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72468
    Prev
    Next
    INDEX
    Explanations

    specific kinds of people or things

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

    The neuron strongly activates on longer, multi-syllable, domain-specific content words (e.g. technical nouns and formal terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    }$.
    -1.64
    ?).
    -1.45
    %).
    -1.38
    ].
    -1.34
    明日は
    -1.29
     rése
    -1.28
    //};
    -1.28
    ).
    -1.28
    "].
    -1.27
    }}$.
    -1.25
    POSITIVE LOGITS
    )
    1.18
     tipo
    1.16
     will
    1.14
    ších
    1.13
    UCIÓN
    1.12
    もありますが
    1.11
    ,
    1.10
    不
    1.09
    もあって
    1.09
    şik
    1.08
    Activations Density 0.181%

    No Known Activations