© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110607
    Prev
    Next
    INDEX
    Explanations

    Argentina Buenos Aires

    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
    されていました
    -0.87
     Fitting
    -0.81
    思います
    -0.79
    ьте
    -0.75
     Smoking
    -0.73
    していました
    -0.72
    Betyg
    -0.71
    astre
    -0.71
    笑笑
    -0.70
    føl
    -0.69
    POSITIVE LOGITS
    同步
    0.75
    ⑤
    0.75
    ="'+
    0.74
    andidate
    0.73
    অ
    0.73
    Sync
    0.73
    IBarButtonItem
    0.72
     大型
    0.71
     raster
    0.70
    ħ
    0.69
    Activations Density 0.011%

    No Known Activations