© 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. 102392
    Prev
    Next
    INDEX
    Explanations

    license, http, predictor, free software

    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
    entr
    -0.82
    krank
    -0.71
    Fak
    -0.69
    xf
    -0.69
     resizing
    -0.69
    orated
    -0.68
     Saat
    -0.68
     stab
    -0.67
    iedz
    -0.67
     gamer
    -0.67
    POSITIVE LOGITS
    話す
    0.77
     Amman
    0.69
    راهيم
    0.69
    writeFieldEnd
    0.69
     awareness
    0.69
    Awareness
    0.66
    MCD
    0.66
    စ
    0.65
    為何
    0.64
     Clegg
    0.64
    Activations Density 0.056%

    No Known Activations