© 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. 218498
    Prev
    Next
    INDEX
    Explanations

    lists of slots

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

    Guardianship, narrative, append, catastrophic, significant, improved, disruptive

    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
     ابراہیم
    0.54
     Ispol
    0.52
     caoutch
    0.50
     órg
    0.49
     тим
    0.49
    秆
    0.49
     الصي
    0.48
     لوگوں
    0.48
     инструмент
    0.47
     встречи
    0.47
    POSITIVE LOGITS
     shopping
    0.59
    NC
    0.57
    NH
    0.57
    *
    0.57
    TA
    0.54
    ahl
    0.53
    SK
    0.53
    MA
    0.53
     left
    0.51
    2
    0.51
    Activations Density 0.000%

    No Known Activations