© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241467
    Prev
    Next
    INDEX
    Explanations

    within versus

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    وید
    0.64
    વવા
    0.64
    召唤
    0.61
    イヤー
    0.57
     *)&
    0.57
    dessus
    0.57
    લિ
    0.57
    виться
    0.57
    summon
    0.57
    敨
    0.57
    POSITIVE LOGITS
     within
    0.79
     Within
    0.73
    /
    0.71
     أت
    0.71
     Fres
    0.70
     versus
    0.70
     vs
    0.69
     Сот
    0.69
     Dentro
    0.68
     hybrids
    0.64
    Activations Density 0.001%

    No Known Activations