© 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. 130138
    Prev
    Next
    INDEX
    Explanations

    sponsored by, header file

    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
     is
    -1.45
     ۶
    -1.05
     daraus
    -0.96
     tackle
    -0.94
     להשת
    -0.93
    ATAR
    -0.92
    tplatz
    -0.91
    チョイス
    -0.91
    薅
    -0.90
    דים
    -0.90
    POSITIVE LOGITS
     which
    1.52
     or
    1.30
     coloridos
    1.03
     których
    0.93
     prv
    0.92
     memasak
    0.91
    šnje
    0.91
     that
    0.91
    Producto
    0.89
     ambao
    0.87
    Activations Density 0.140%

    No Known Activations