© 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. 15107
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     EBITDA
    0.16
     BLM
    0.15
     وكل
    0.14
     χ
    0.14
     ピンク
    0.14
     ∆
    0.14
    हील
    0.14
     डिपॉ
    0.14
     θέ
    0.14
     автор
    0.14
    POSITIVE LOGITS
    <unused63>
    0.19
    <unused62>
    0.18
    <unused61>
    0.18
    <unused60>
    0.17
    res
    0.15
    Url
    0.15
    Environment
    0.14
    Data
    0.13
    0.13
    Provider
    0.13
    Activations Density 0.013%

    No Known Activations