© 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. 75712
    Prev
    Next
    INDEX
    Explanations

    lists, numbers, or categories

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

    attacker exploits and security awareness

    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
    Negative Logits
    и
    0.47
     Rudd
    0.45
     marginalized
    0.44
     disproportion
    0.42
     barista
    0.41
     encountering
    0.41
     magn
    0.41
    ποτε
    0.41
     vores
    0.41
     rusk
    0.41
    POSITIVE LOGITS
    '));
    0.55
    torio
    0.48
    拼接
    0.47
    ')));
    0.47
    fänger
    0.47
     ছুটি
    0.45
    ないので
    0.45
    yse
    0.45
    หน้า
    0.44
     consecutivos
    0.44
    Activations Density 0.001%

    No Known Activations