© 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. 14866
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    ‌లు
    0.56
    utenant
    0.56
    班
    0.55
    onaldo
    0.54
     !!,
    0.54
    conclusion
    0.53
    蠹
    0.52
    κος
    0.51
    uccino
    0.51
    LaunchScheme
    0.51
    POSITIVE LOGITS
    etera
    1.16
    …).
    1.15
     cetera
    1.13
    …
    1.04
    etra
    1.03
    …)
    1.02
    ETER
    0.95
    ...).
    0.95
     …
    0.89
    …]
    0.89
    Activations Density 0.020%

    No Known Activations