© 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. 109193
    Prev
    Next
    INDEX
    Explanations

    safest defenses

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

    following descriptive sequences

    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
    ভিশ
    0.51
    раль
    0.45
    네
    0.45
    тите
    0.44
    лі
    0.43
    expansive
    0.43
    appliquer
    0.42
    тара
    0.42
    యితే
    0.42
    تباين
    0.41
    POSITIVE LOGITS
     ð
    0.47
     রক্ষা
    0.47
     juz
    0.47
     avoids
    0.46
     defends
    0.46
     (
    0.46
     haz
    0.44
     romantic
    0.43
     காணலாம்
    0.43
     பணியாற்ற
    0.43
    Activations Density 0.004%

    No Known Activations