© 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. 65232
    Prev
    Next
    INDEX
    Explanations

    programming and science contexts

    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
     want
    -0.90
    เก
    -0.82
    才是
    -0.76
     làng
    -0.75
     tokenId
    -0.75
     Drawing
    -0.75
    <!--[
    -0.74
     from
    -0.73
     puppies
    -0.73
     ruinas
    -0.73
    POSITIVE LOGITS
    катерина
    0.92
    𝚟
    0.83
     ebbe
    0.83
     delà
    0.79
    inerario
    0.79
     ";"
    0.77
    ⫸
    0.76
    heta
    0.76
    眯
    0.76
    पुर
    0.75
    Activations Density 0.002%

    No Known Activations