© 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. 17680
    Prev
    Next
    INDEX
    Explanations

    terms followed by punctuation

    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
     coats
    0.45
     sensibility
    0.45
     clumps
    0.45
    眩
    0.44
     rays
    0.44
     lamps
    0.43
     ressort
    0.43
     chloroform
    0.42
     ش
    0.42
     clump
    0.42
    POSITIVE LOGITS
     έχει
    0.54
     अध्ययन
    0.50
    avacanam
    0.50
    愔
    0.49
    Пред
    0.49
    ivables
    0.49
    avacan
    0.48
     thiab
    0.48
     Thánh
    0.48
     menyampaikan
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.