© 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. 10-GEMMASCOPE-RES-131K
    7. 43319
    Prev
    Next
    INDEX
    Explanations

    accepting things

    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_10/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
    i
    -3.64
    ar
    -3.61
    os
    -3.03
    ي
    -3.02
    い
    -2.94
    y
    -2.89
     to
    -2.89
    mu
    -2.83
    (
    -2.80
     be
    -2.73
    POSITIVE LOGITS
    ୌ
    3.08
    錞
    3.03
    頽
    2.88
    柃
    2.88
    戩
    2.88
    bernador
    2.86
     secado
    2.78
    礽
    2.75
    Langkah
    2.73
     fournies
    2.73
    Activations Density 0.010%

    No Known Activations