© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60213
    Prev
    Next
    INDEX
    Explanations

    skin treatments

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

    words related to responses or replies in communication contexts.

    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
    }
    -2.28
    ing
    -2.20
    }$
    -2.20
    what
    -2.19
    -1.87
    after
    -1.84
     or
    -1.80
    What
    -1.78
    from
    -1.78
    a
    -1.70
    POSITIVE LOGITS
    “
    2.14
     curar
    1.89
     dragón
    1.89
     urges
    1.88
    憷
    1.87
     vendita
    1.84
     hígado
    1.79
     indiví
    1.77
    </em>
    1.76
    ımıza
    1.73
    Activations Density 0.000%

    No Known Activations