© 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. 241341
    Prev
    Next
    INDEX
    Explanations

    own page

    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
    Hei
    0.61
    pSensor
    0.58
    -(-
    0.58
    UMS
    0.58
    poline
    0.57
    Dll
    0.56
    Volvo
    0.55
    액
    0.55
    cnf
    0.55
    encoders
    0.55
    POSITIVE LOGITS
     own
    0.77
     page
    0.77
     mortar
    0.73
     kendi
    0.71
     mortars
    0.71
     propia
    0.70
     eigenen
    0.70
     webpage
    0.70
     FB
    0.67
     SCR
    0.66
    Activations Density 0.001%

    No Known Activations