© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3463
    Prev
    Next
    INDEX
    Explanations

    height, weight, or size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    라도
    0.76
    라고
    0.74
    !).
    0.72
    WARDS
    0.71
    나
    0.71
    l
    0.70
    !*\
    0.69
    스로
    0.68
     ล่ะ
    0.68
    ap
    0.68
    POSITIVE LOGITS
     is
    1.02
     provides
    0.91
     pode
    0.88
     has
    0.87
     encephalitis
    0.84
     peut
    0.82
     используется
    0.82
     caries
    0.82
     facilitates
    0.80
     muestra
    0.80
    Activations Density 0.001%

    No Known Activations