© 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. 22-GEMMASCOPE-RES-131K
    7. 95705
    Prev
    Next
    INDEX
    Explanations

    API query parameters

    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
     if
    -1.31
     for
    -1.02
     FOR
    -1.00
    迥
    -0.99
     from
    -0.99
     with
    -0.98
     gyvento
    -0.97
     in
    -0.96
    onaldo
    -0.94
     Dua
    -0.92
    POSITIVE LOGITS
    ά
    1.13
    誰が
    1.12
    FUENTE
    1.09
     current
    1.08
     состояние
    1.06
    有無
    1.05
     state
    1.05
    lámpara
    1.02
     status
    1.02
     cozinha
    1.02
    Activations Density 0.005%

    No Known Activations