© 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. 241546
    Prev
    Next
    INDEX
    Explanations

    specific names or things

    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
    ophones
    0.68
     بوا
    0.61
    堷
    0.60
    woord
    0.59
     tomates
    0.57
    awah
    0.55
    oč
    0.55
     différences
    0.55
    bart
    0.54
    čnosti
    0.54
    POSITIVE LOGITS
    Ղ
    0.58
     Cav
    0.55
     cloak
    0.54
    অতি
    0.54
     queryObject
    0.53
     leg
    0.53
    Ժ
    0.52
    饋
    0.51
    cav
    0.50
     footer
    0.50
    Activations Density 0.000%

    No Known Activations