© 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-262K
    7. 241520
    Prev
    Next
    INDEX
    Explanations

    MMA media and fighters

    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_262k_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
     guava
    0.69
     predators
    0.69
     venen
    0.69
     invertebrates
    0.67
     ऑर्गेना
    0.66
     mulberry
    0.65
    揄
    0.65
    牡
    0.64
    鈕
    0.64
     entr
    0.63
    POSITIVE LOGITS
    junk
    0.62
     Gough
    0.62
    اكم
    0.61
    ServerSocket
    0.61
     Preprint
    0.59
    őtt
    0.59
    mediawiki
    0.58
    Tokenizer
    0.57
    FontSize
    0.57
    нима
    0.56
    Activations Density 0.000%

    No Known Activations