© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65026
    Prev
    Next
    INDEX
    Explanations

    license or associated

    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
     også
    -0.96
     también
    -0.91
    lím
    -0.90
    ATHERINE
    -0.90
    ORET
    -0.89
     quoque
    -0.88
     també
    -0.88
    ก็
    -0.88
     konflikt
    -0.87
     även
    -0.84
    POSITIVE LOGITS
     linked
    0.81
    execu
    0.74
     getting
    0.74
    expédition
    0.73
     Assyrian
    0.72
     how
    0.71
     (_.
    0.70
     αντί
    0.69
    してます
    0.68
     dreapta
    0.67
    Activations Density 0.002%

    No Known Activations