© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    molecular

    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
    Wins
    0.54
    ᅬ
    0.54
     premium
    0.53
    premium
    0.53
     असर
    0.52
     နောက်
    0.52
    ముఖ
    0.52
    攀
    0.52
    رض
    0.52
    ценка
    0.52
    POSITIVE LOGITS
     orbital
    0.85
     orbitals
    0.80
     Orbital
    0.80
     sieve
    0.80
     weight
    0.75
    gewicht
    0.74
     WEIGHT
    0.73
     düzey
    0.73
    orbital
    0.71
    weights
    0.71
    Activations Density 0.009%

    No Known Activations