© 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. 52004
    Prev
    Next
    INDEX
    Explanations

    CID, SII, packet, cash

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

    Google Gemini formerly Bard

    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
     Traveler
    0.48
    ka
    0.48
     С
    0.47
     הס
    0.46
     Storia
    0.46
     Built
    0.46
    re
    0.46
     ו
    0.45
    was
    0.45
    rakt
    0.45
    POSITIVE LOGITS
     axons
    0.54
    \"
    0.50
    しないで
    0.50
    ница
    0.48
     égales
    0.48
     extérieur
    0.48
    ックレス
    0.47
    তেই
    0.47
    ifelse
    0.47
    ⦕
    0.47
    Activations Density 0.000%

    No Known Activations