© 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. 34-GEMMASCOPE-RES-131K
    7. 117366
    Prev
    Next
    INDEX
    Explanations

    copyright NOTICE file

    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
    responseType
    -0.75
    роме
    -0.74
    бал
    -0.73
    otea
    -0.71
    witt
    -0.69
    poni
    -0.67
     once
    -0.67
     бал
    -0.65
    loom
    -0.65
    beschreibung
    -0.63
    POSITIVE LOGITS
     adil
    0.72
    DEFINE
    0.71
     Lichten
    0.71
    Verso
    0.69
    ΑΛ
    0.68
     adik
    0.68
     sonora
    0.68
     gug
    0.67
     suami
    0.65
    Scaler
    0.65
    Activations Density 0.067%

    No Known Activations