Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 188
    Prev
    Next
    INDEX
    Explanations

    Winchester and firearms

    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
     Eche
    -0.83
     ensi
    -0.82
     michelle
    -0.77
    琉
    -0.75
    プローチ
    -0.75
    Kali
    -0.74
     Kali
    -0.73
    BMP
    -0.72
     compli
    -0.71
     fertig
    -0.71
    POSITIVE LOGITS
     wins
    0.82
    Win
    0.81
     lever
    0.81
     win
    0.79
    Pump
    0.76
    matology
    0.74
    保安
    0.73
     Winchester
    0.73
     Pump
    0.71
    bool
    0.69
    Activations Density 0.006%

    No Known Activations