© 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. 55926
    Prev
    Next
    INDEX
    Explanations

    Follow your instructions

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

    security threats and technical systems

    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
    quinoxalin
    0.43
    МИ
    0.43
    nze
    0.42
    Mama
    0.42
    [-
    0.41
     reinforcements
    0.41
    [
    0.41
    ức
    0.41
     regimens
    0.41
    Mât
    0.41
    POSITIVE LOGITS
     魔
    0.48
     मैनेज
    0.47
     クラ
    0.45
     നടത്തി
    0.45
     നടന്ന
    0.45
     κο
    0.45
     ஏனெனில்
    0.45
     子
    0.45
     の
    0.44
     เท
    0.44
    Activations Density 0.000%

    No Known Activations