© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202968
    Prev
    Next
    INDEX
    Explanations

    business or obtaining packages

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

    associated with malware

    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
     IFC
    0.47
    m
    0.46
     był
    0.46
     JOHNSON
    0.45
    igheid
    0.45
    issant
    0.45
    haber
    0.44
     Davos
    0.44
    \
    0.44
     Would
    0.44
    POSITIVE LOGITS
    異なる
    0.54
     ライン
    0.48
    ﾏ
    0.46
    раста
    0.46
     અન્ય
    0.45
    異なります
    0.44
    𝙉
    0.44
     разно
    0.44
    দ্বার
    0.43
     amplitudes
    0.43
    Activations Density 0.002%

    No Known Activations