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. 8444
    Prev
    Next
    INDEX
    Explanations

    android method signatures

    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
    その他
    -0.85
     these
    -0.81
     particularly
    -0.79
     especially
    -0.77
    ココ
    -0.77
     muualla
    -0.74
     besonders
    -0.73
    ティア
    -0.69
     شنا
    -0.69
     suivante
    -0.69
    POSITIVE LOGITS
    kana
    0.94
     it
    0.90
     FLE
    0.87
    还是
    0.85
    rall
    0.80
     toh
    0.79
    وث
    0.79
     HEL
    0.79
     var
    0.79
     BED
    0.79
    Activations Density 0.007%

    No Known Activations