© 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. 187468
    Prev
    Next
    INDEX
    Explanations

    services, consultation, industry, safety

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

    most clear and thorough

    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
    大规模
    0.49
    サン
    0.48
    Это
    0.48
    にい
    0.47
    blastoma
    0.47
    梂
    0.47
    Rear
    0.47
    なん
    0.46
    Liste
    0.46
    tevõ
    0.46
    POSITIVE LOGITS
     Potenz
    0.43
    רים
    0.43
     सावधान
    0.43
     الجيش
    0.42
     e
    0.41
    ees
    0.40
     Cook
    0.40
    eur
    0.40
    elim
    0.40
    elez
    0.40
    Activations Density 0.000%

    No Known Activations