© 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. 22-GEMMASCOPE-RES-131K
    7. 38386
    Prev
    Next
    INDEX
    Explanations

    code and technical keywords

    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_22/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
     spannende
    -0.99
    尬
    -0.92
     Sosial
    -0.91
    どうやら
    -0.90
    OBJETIVO
    -0.88
    CAPÍTULO
    -0.86
     уголов
    -0.85
    tens
    -0.84
    话音
    -0.83
    isst
    -0.81
    POSITIVE LOGITS
    ())));
    0.98
     only
    0.97
    ToBounds
    0.96
    ();
    0.92
    پس
    0.92
    Não
    0.92
    isDebugEnabled
    0.91
    klady
    0.91
    𝐑
    0.90
    ()]
    0.90
    Activations Density 0.016%

    No Known Activations