© 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. 85178
    Prev
    Next
    INDEX
    Explanations

    travelling road and titanium sedan

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

    SQL injection attempt

    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
    ک
    0.51
    テナンス
    0.50
    ュ
    0.50
    ूल
    0.49
    ⴱ
    0.49
    کار
    0.48
    ография
    0.48
    का
    0.48
     встречи
    0.47
    フラ
    0.47
    POSITIVE LOGITS
     protrusion
    0.51
    `:
    0.46
    apper
    0.44
    stringProp
    0.44
     capitalise
    0.43
     string
    0.42
     mach
    0.42
     byte
    0.42
    strlen
    0.42
     odstr
    0.42
    Activations Density 0.000%

    No Known Activations