© 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. 63067
    Prev
    Next
    INDEX
    Explanations

    copyright notices and comments

    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
    veston
    -0.77
     इत
    -0.76
     Reine
    -0.73
     сообщили
    -0.71
    zeum
    -0.71
    賛
    -0.70
    ULO
    -0.70
    vings
    -0.70
    ैन
    -0.69
    嚷
    -0.69
    POSITIVE LOGITS
    Když
    0.96
    forsk
    0.82
    gaja
    0.81
     KING
    0.79
    Cliquez
    0.79
    א
    0.78
    ernoo
    0.78
    Díky
    0.76
     erd
    0.76
     प्रोडक्ट
    0.75
    Activations Density 0.007%

    No Known Activations