© 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. 15307
    Prev
    Next
    INDEX
    Explanations

    water flow

    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
    舰
    0.63
     vaisseaux
    0.61
     кораб
    0.58
    غرب
    0.57
     ships
    0.57
    🛳
    0.57
     জাহাজ
    0.55
    ratingBarStyle
    0.55
     airports
    0.53
     শ্বাস
    0.53
    POSITIVE LOGITS
     waterfall
    2.25
     waterfalls
    2.09
     Waterfall
    2.00
    Waterfall
    1.95
     cascades
    1.83
    瀑
    1.78
     cascade
    1.77
     cascading
    1.75
    cascade
    1.65
    滝
    1.63
    Activations Density 0.102%

    No Known Activations