© 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. 15034
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    parad
    0.59
     paradise
    0.58
     Bous
    0.57
     Orth
    0.56
    OSR
    0.55
     ĝ
    0.54
     bt
    0.54
     thử
    0.54
    Parad
    0.53
    のかな
    0.52
    POSITIVE LOGITS
     വിഭാഗ
    0.59
     ವಿರು
    0.58
     vajj
    0.57
    цеп
    0.56
     схема
    0.55
    ファイ
    0.54
    弛
    0.52
     компонен
    0.52
    繊維
    0.51
     структур
    0.50
    Activations Density 0.000%

    No Known Activations