© 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. 3409
    Prev
    Next
    INDEX
    Explanations

    media file paths

    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
    osynthesis
    0.40
    ଼
    0.40
     Approximate
    0.40
     লক্ষ্যে
    0.39
    läuft
    0.39
    Indexing
    0.38
     Statistical
    0.37
    Manufacturer
    0.37
    рак
    0.37
     computations
    0.36
    POSITIVE LOGITS
    PLAY
    0.41
     మీడి
    0.41
     medya
    0.41
    FORCE
    0.39
     mediana
    0.39
    Ր
    0.39
     சீ
    0.38
    yana
    0.38
    麒
    0.38
     malam
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.