© 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. 5931
    Prev
    Next
    INDEX
    Explanations

    chess game

    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
    re
    2.09
    tt
    1.78
    у
    1.66
    d
    1.64
    и
    1.61
    j
    1.56
    ल
    1.52
    ii
    1.51
    aj
    1.42
     Eing
    1.42
    POSITIVE LOGITS
    ח
    1.73
    ानी
    1.73
    нным
    1.60
    ыл
    1.59
    ोग
    1.57
     указыва
    1.50
    ர்
    1.48
    ك
    1.48
    ﻐ
    1.48
    را
    1.46
    Activations Density 0.002%

    No Known Activations