© 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. 233261
    Prev
    Next
    INDEX
    Explanations

    completing development programs requires

    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
    تاب
    0.44
    -
    0.42
    étale
    0.41
    computers
    0.41
    ،
    0.41
     (
    0.40
     ஆரோக்கிய
    0.39
     Duterte
    0.39
     ঢাকা
    0.39
    はじ
    0.39
    POSITIVE LOGITS
     timeouts
    0.47
    इकिल
    0.46
     TRUE
    0.44
    㭋
    0.44
    িয়াছি
    0.43
     outliers
    0.43
     TEXT
    0.42
    エス
    0.42
     crick
    0.42
     σύμφωνα
    0.42
    Activations Density 0.002%

    No Known Activations