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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7878
    Prev
    Next
    INDEX
    Explanations

    Tobacco Industry, 0 Shares, Provides two

    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
    tilhar
    -0.89
    thora
    -0.79
    зов
    -0.77
     centrales
    -0.75
    пили
    -0.72
     there
    -0.71
    freude
    -0.71
     Tübingen
    -0.69
    威力
    -0.69
     quite
    -0.69
    POSITIVE LOGITS
    maxcdn
    1.02
    stuffs
    0.84
    cuz
    0.82
     bootstra
    0.82
    compressor
    0.82
     beno
    0.81
    惊艳
    0.81
    MING
    0.78
     還
    0.78
    mentions
    0.77
    Activations Density 0.005%

    No Known Activations