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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57115
    Prev
    Next
    INDEX
    Explanations

    new graphics / performance graphics

    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
    ďte
    -0.85
     these
    -0.81
    顼
    -0.81
    putInt
    -0.80
    بية
    -0.79
    věř
    -0.78
    ****/
    -0.77
    atlantic
    -0.77
    nuevos
    -0.77
     undersø
    -0.76
    POSITIVE LOGITS
    ⇡
    1.09
    Epilogue
    0.95
    mbangkan
    0.88
    ार्
    0.88
    Sweep
    0.84
    Declared
    0.83
     стар
    0.83
     enthusiast
    0.83
    辈
    0.82
     representatives
    0.82
    Activations Density 0.023%

    No Known Activations