© 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. 15292
    Prev
    Next
    INDEX
    Explanations

    not

    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
     fi
    0.81
    fi
    0.77
    fl
    0.74
    ‟
    0.71
     requisite
    0.66
     
    0.64
     ordinarily
    0.62
     ©
    0.62
    ೨
    0.59
     exceedingly
    0.58
    POSITIVE LOGITS
     ,
    0.79
     entanto
    0.75
    Namun
    0.75
     Namun
    0.70
     jedoch
    0.66
    However
    0.62
     echter
    0.62
     ,"
    0.62
     sogenannte
    0.60
     however
    0.59
    Activations Density 0.003%

    No Known Activations