© 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. 70243
    Prev
    Next
    INDEX
    Explanations

    home and closeness

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     There
    -1.77
    }
    -1.68
    There
    -1.63
    ;
    -1.58
    </th>
    -1.55
     она
    -1.55
     It
    -1.52
     there
    -1.49
    _
    -1.48
    </h1>
    -1.47
    POSITIVE LOGITS
     for
    1.53
     IBRARY
    1.48
    綺麗に
    1.46
     matic
    1.41
    ことも
    1.39
    渽
    1.38
     Gennaio
    1.38
    暖かい
    1.38
    tômes
    1.36
     vespa
    1.36
    Activations Density 0.015%

    No Known Activations