© 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. 65155
    Prev
    Next
    INDEX
    Explanations

    replaceSQLhttpusbTerry

    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
    ---->
    -0.79
    <0xA3>
    -0.79
     деле
    -0.78
     çocuk
    -0.76
    は
    -0.76
    interesting
    -0.75
     fungi
    -0.75
    lvl
    -0.74
    voegd
    -0.74
     siguiente
    -0.73
    POSITIVE LOGITS
     novices
    0.94
    cumin
    0.94
     violences
    0.91
    EARCH
    0.90
    ₱
    0.89
     protoimpl
    0.89
    vernote
    0.87
    ⎨
    0.87
    oare
    0.87
    レント
    0.86
    Activations Density 0.008%

    No Known Activations