© 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. 241489
    Prev
    Next
    INDEX
    Explanations

    initialization code

    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
    AG
    0.73
    寄
    0.64
    utch
    0.61
    شک
    0.60
     법칙
    0.58
    ্টার
    0.56
    ohl
    0.55
    obes
    0.55
    ꯕ
    0.55
     exped
    0.55
    POSITIVE LOGITS
     druk
    0.67
     Flächen
    0.64
     Flatten
    0.64
     dorp
    0.63
     Irene
    0.61
     PRINT
    0.61
    φέρ
    0.61
     Padding
    0.60
     Fem
    0.60
     كي
    0.60
    Activations Density 0.000%

    No Known Activations