© 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. 236443
    Prev
    Next
    INDEX
    Explanations

    actions and unauthorized access

    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
    ﺟ
    0.55
     ench
    0.47
     могу
    0.45
     commentaires
    0.43
    辛苦
    0.43
     జి
    0.43
     испан
    0.42
    墨西哥
    0.42
    裕
    0.42
    命
    0.42
    POSITIVE LOGITS
     Rack
    0.52
    boru
    0.51
    hna
    0.50
     symbolize
    0.50
     Launch
    0.50
     Run
    0.49
     Always
    0.48
    simulate
    0.48
    kin
    0.48
    ton
    0.47
    Activations Density 0.000%

    No Known Activations