© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14817
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Như
    0.59
     করেই
    0.59
    печат
    0.56
     replaces
    0.54
    Simply
    0.53
     duy
    0.52
    뉘
    0.52
     Tere
    0.51
    व्यक्तित्व
    0.51
    땃
    0.51
    POSITIVE LOGITS
     smith
    0.60
     jones
    0.58
    Smith
    0.58
    ந்திரன்
    0.57
    smith
    0.56
     Accountant
    0.56
    <unused1984>
    0.56
     स्मिथ
    0.56
     Acme
    0.55
     महत्त्वा
    0.55
    Activations Density 0.049%

    No Known Activations