© 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. 241340
    Prev
    Next
    INDEX
    Explanations

    academic and technical context

    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
    ongoose
    0.59
    侾
    0.58
     MHC
    0.56
    亻
    0.56
    aziland
    0.55
    īgi
    0.54
     usurp
    0.54
    䋇
    0.54
    )|$(
    0.53
     lymphoid
    0.53
    POSITIVE LOGITS
     নিতান্ত
    0.59
     お客様
    0.56
    優れた
    0.54
     멋
    0.54
     অত্যন্ত
    0.54
    שוט
    0.54
     Learners
    0.53
     تم
    0.52
     bello
    0.52
     traceable
    0.52
    Activations Density 0.000%

    No Known Activations