© 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. 6036
    Prev
    Next
    INDEX
    Explanations

    sum of subarray ranges

    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
    1
    1.20
    2
    1.09
     in
    1.04
    in
    1.00
    4
    0.92
    3
    0.91
    IN
    0.90
    5
    0.90
    7
    0.90
    A
    0.90
    POSITIVE LOGITS
     været
    0.93
     byla
    0.89
     của
    0.87
     tuvo
    0.85
     judiciaire
    0.85
     hade
    0.84
     consente
    0.84
     sufrió
    0.84
     vært
    0.84
     été
    0.82
    Activations Density 2.965%

    No Known Activations