© 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. 90507
    Prev
    Next
    INDEX
    Explanations

    problems asking how to

    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
     However
    -0.91
     сюда
    -0.76
    ☑️
    -0.75
    uegos
    -0.74
     Negroes
    -0.73
    {#
    -0.73
    而
    -0.72
    itzende
    -0.71
     lightly
    -0.71
     heavily
    -0.71
    POSITIVE LOGITS
     in
    1.04
    ってみる
    0.94
     в
    0.93
     разница
    0.89
    囮
    0.88
    turquoise
    0.85
    等は
    0.85
    不高
    0.84
     museos
    0.84
     семья
    0.84
    Activations Density 0.019%

    No Known Activations