© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109763
    Prev
    Next
    INDEX
    Explanations

    protected email addresses and urls

    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
    འ
    -0.88
     szeptember
    -0.84
     уголов
    -0.83
    札幌
    -0.81
    思います
    -0.80
    耨
    -0.79
    日本酒
    -0.79
     Lockhart
    -0.77
    这让
    -0.77
    라는
    -0.77
    POSITIVE LOGITS
     protected
    1.45
    protected
    1.41
    Protected
    1.15
     Protected
    1.13
     roli
    0.98
     Removed
    0.96
    Removed
    0.95
    ],[
    0.95
     withheld
    0.94
     removed
    0.94
    Activations Density 0.021%

    No Known Activations