© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239156
    Prev
    Next
    INDEX
    Explanations

    tested items and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ری
    0.51
    ج
    0.46
    ेट
    0.46
    лому
    0.45
     renewals
    0.45
    िक
    0.44
    ून
    0.43
    ন
    0.43
    濯
    0.43
    ان
    0.42
    POSITIVE LOGITS
     dementia
    0.54
     spé
    0.53
     Macbook
    0.53
     dyslex
    0.52
     coch
    0.52
     distinto
    0.51
     dement
    0.50
     mache
    0.50
     measles
    0.49
     cra
    0.49
    Activations Density 0.000%

    No Known Activations