© 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. 101435
    Prev
    Next
    INDEX
    Explanations

    cytoskeletal

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

    The neuron is identifying words related to job positions or occupations, particularly service roles like "waiter" and "waiters".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    吖
    -2.83
    睺
    -2.67
    ματος
    -2.67
     哪些
    -2.66
     队
    -2.63
     碎
    -2.59
    暻
    -2.59
    葑
    -2.58
    ſſen
    -2.53
     लेकिन
    -2.53
    POSITIVE LOGITS
    </i>
    3.80
     
    3.56
    -
    3.44
    This
    2.91
     Their
    2.91
     When
    2.83
     Such
    2.81
     It
    2.78
    }
    2.58
    --
    2.56
    Activations Density 0.002%

    No Known Activations