© 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. 22-GEMMASCOPE-RES-131K
    7. 129373
    Prev
    Next
    INDEX
    Explanations

    that is, introducing explanation

    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_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
     and
    -2.28
    7
    -1.69
    ">
    -1.68
    ⩩
    -1.64
    過的
    -1.63
    蹓
    -1.62
    <td>
    -1.61
    ();
    -1.60
    ulous
    -1.59
    issances
    -1.57
    POSITIVE LOGITS
    ,
    1.77
     why
    1.62
     if
    1.56
     Which
    1.47
     “
    1.44
     prioriti
    1.38
     \
    1.36
    三人
    1.33
     We
    1.32
    眨眼
    1.31
    Activations Density 0.011%

    No Known Activations