© 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. 218750
    Prev
    Next
    INDEX
    Explanations

    corporate events

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

    Character First, Delayed Intervention, Local Script

    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
    up
    0.44
    （
    0.40
    千
    0.40
    рт
    0.39
    ств
    0.38
     CANT
    0.38
     terme
    0.38
    ض
    0.38
    im
    0.38
    木
    0.37
    POSITIVE LOGITS
    ี้ยง
    0.51
    ന്ത്ര
    0.50
     Đài
    0.50
     രണ്ട്
    0.50
     വിഷ
    0.49
     ولی
    0.49
     Дру
    0.49
     Вот
    0.49
     తగ్
    0.49
    𒋙
    0.49
    Activations Density 0.000%

    No Known Activations