© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15327
    Prev
    Next
    INDEX
    Explanations

    numerical and defined items

    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
    granular
    0.68
    鑰
    0.59
    膵
    0.59
     Therapist
    0.57
    chende
    0.56
     Vessel
    0.55
     조직
    0.54
    entering
    0.54
    涸
    0.54
    тров
    0.52
    POSITIVE LOGITS
     AC
    0.61
     AE
    0.54
     rebell
    0.54
     num
    0.53
     FA
    0.53
     caught
    0.52
     ঘটনা
    0.52
     kuri
    0.52
     vari
    0.52
     bi
    0.52
    Activations Density 0.000%

    No Known Activations