© 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. 229100
    Prev
    Next
    INDEX
    Explanations

    percentages, days, paper, unique, later

    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
    Slice
    0.50
    𝗶
    0.49
    gge
    0.48
    াপি
    0.47
     Фургал
    0.47
     sluč
    0.46
    狹
    0.46
    좌
    0.46
    ని
    0.45
    posição
    0.45
    POSITIVE LOGITS
     http
    0.53
     Main
    0.49
     sincere
    0.48
     its
    0.47
     Martin
    0.47
     Mack
    0.47
     Bre
    0.46
     Behav
    0.45
     Raymond
    0.45
     a
    0.45
    Activations Density 0.000%

    No Known Activations