© 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. 54362
    Prev
    Next
    INDEX
    Explanations

    code comments and structured text

    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
     begins
    -0.71
     posición
    -0.69
    routs
    -0.69
    兮
    -0.69
     भाव
    -0.67
     Kanto
    -0.67
    TokenNameRBRACE
    -0.65
    heating
    -0.64
    decode
    -0.64
     Conch
    -0.64
    POSITIVE LOGITS
    ῦ
    0.76
     Werk
    0.68
     Beschäf
    0.67
     Catholicism
    0.63
     aftermath
    0.63
    glPopMatrix
    0.63
    ждане
    0.62
     Gesam
    0.62
    beeren
    0.62
     مخطط
    0.61
    Activations Density 0.073%

    No Known Activations