© 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. 75823
    Prev
    Next
    INDEX
    Explanations

    type casting or conversion

    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
     somit
    -0.84
     something
    -0.83
    iern
    -0.82
    uxedo
    -0.81
    дәбият
    -0.80
     STEIN
    -0.74
    美味しいです
    -0.74
     prowadzi
    -0.74
    UVW
    -0.74
     qualquer
    -0.74
    POSITIVE LOGITS
     from
    1.38
    string
    1.18
    sender
    1.11
    uint
    1.06
    bool
    0.98
     decimal
    0.96
    byte
    0.95
    ?(
    0.93
    foreach
    0.92
    from
    0.92
    Activations Density 0.002%

    No Known Activations