© 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-65K
    7. 15280
    Prev
    Next
    INDEX
    Explanations

    diverse topics

    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_65k_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
    속
    0.57
    स्पीड
    0.52
    ឬ
    0.50
     RESET
    0.50
     reset
    0.49
     PRIMARY
    0.49
     Pound
    0.49
    鷸
    0.48
    primary
    0.48
     சிறி
    0.48
    POSITIVE LOGITS
    ErrorReport
    0.58
    Lor
    0.58
     Lor
    0.54
     tiket
    0.53
     препаратов
    0.53
     излу
    0.53
    氹
    0.52
     तह
    0.51
    Fet
    0.51
     comment
    0.51
    Activations Density 0.000%

    No Known Activations