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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80740
    Prev
    Next
    INDEX
    Explanations

    git diff blame

    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
    FECT
    -0.91
    fect
    -0.79
     Dau
    -0.77
    perse
    -0.75
    Balan
    -0.74
     Fait
    -0.73
    rada
    -0.73
     augustus
    -0.71
    傻
    -0.70
    VIOUS
    -0.69
    POSITIVE LOGITS
     diff
    1.19
     blame
    1.13
    diff
    1.00
     Diff
    1.00
    Diff
    0.99
    blame
    0.96
     Blame
    0.95
    Blame
    0.92
    DIFF
    0.90
    Lines
    0.86
    Activations Density 0.051%

    No Known Activations