© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76348
    Prev
    Next
    INDEX
    Explanations

    Ext JS code

    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_34/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
     amyloid
    -0.73
    čnega
    -0.73
    cstdlib
    -0.71
    Ạ
    -0.70
    selin
    -0.70
     Motiv
    -0.70
     posY
    -0.69
     cif
    -0.68
    ల
    -0.68
     thuật
    -0.68
    POSITIVE LOGITS
     MOD
    0.97
     TVs
    0.89
    tv
    0.85
     getResources
    0.83
    xp
    0.82
     snippet
    0.82
     tv
    0.81
     Sni
    0.79
     cães
    0.79
     lòng
    0.78
    Activations Density 0.006%

    No Known Activations