© 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. 177389
    Prev
    Next
    INDEX
    Explanations

    religious or exclusive goods

    np_acts-logits-general · gemini-2.5-flash-lite

    exploited vulnerabilities, steal, intercept

    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
    data
    0.52
    кистон
    0.52
    ar
    0.50
    銀行
    0.50
    国
    0.50
    Iran
    0.49
    家庭
    0.49
    ですよね
    0.49
    ad
    0.48
    atam
    0.47
    POSITIVE LOGITS
     galera
    0.50
     ανάπτυ
    0.49
     gł
    0.48
     легко
    0.47
     զ
    0.47
     搭
    0.47
     fertig
    0.47
     頭
    0.46
     仮
    0.46
     pły
    0.46
    Activations Density 0.000%

    No Known Activations