© 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. 24-GEMMASCOPE-2-RES-262K
    7. 1776
    Prev
    Next
    INDEX
    Explanations

    run script or array

    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_24_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
     a
    0.63
     these
    0.60
     this
    0.57
     czym
    0.50
     u
    0.49
    Paxos
    0.48
    මක්
    0.48
    товые
    0.46
     هذه
    0.46
    amir
    0.45
    POSITIVE LOGITS
     andRow
    0.52
    藠
    0.49
    先端
    0.47
     tandis
    0.47
     καθώς
    0.46
     대신
    0.46
     ткани
    0.44
     («
    0.44
    atic
    0.44
    ቆዳ
    0.44
    Activations Density 0.030%

    No Known Activations