© 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. 15130
    Prev
    Next
    INDEX
    Explanations

    technical code fragments

    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
     fx
    0.53
    敛
    0.51
    झे
    0.50
    汞
    0.50
     জে
    0.50
     SupCt
    0.50
     efek
    0.49
     corret
    0.48
     spé
    0.48
    hendis
    0.48
    POSITIVE LOGITS
    ッシング
    0.58
    嗣
    0.57
     })_{
    0.56
    ნიშვნელ
    0.56
    Nun
    0.55
    に向けて
    0.55
    powr
    0.54
    ător
    0.53
    իմ
    0.53
     Tommy
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.