© 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. 241378
    Prev
    Next
    INDEX
    Explanations

    election outcomes or achievements

    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
    ജാ
    0.58
    iviato
    0.55
    BtnFill
    0.55
    蹈
    0.55
     Nus
    0.54
    놋
    0.54
     revolving
    0.53
    Heroes
    0.53
     එව
    0.53
    resol
    0.53
    POSITIVE LOGITS
     shrinkage
    0.69
     Pour
    0.62
     जलाशय
    0.61
    ڑا
    0.61
     turbulence
    0.61
     roughness
    0.61
     Watershed
    0.57
    Pour
    0.56
    ள்ளதாக
    0.55
    鈎
    0.55
    Activations Density 0.001%

    No Known Activations