© 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. 241368
    Prev
    Next
    INDEX
    Explanations

    structured data input

    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
     iconic
    0.63
    cinema
    0.61
     rights
    0.60
    mun
    0.57
    对此
    0.57
    achery
    0.57
     critical
    0.57
    肖
    0.57
    icon
    0.56
    ৫৮
    0.56
    POSITIVE LOGITS
    まだまだ
    0.63
     assurent
    0.63
     iedere
    0.63
     asegurarse
    0.62
    дете
    0.61
     Jerez
    0.61
     इजीली
    0.61
     Plenty
    0.59
     Easily
    0.58
     neutralize
    0.58
    Activations Density 0.000%

    No Known Activations