© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112397
    Prev
    Next
    INDEX
    Explanations

    Korean terms, indexes, markers

    np_acts-logits-general · gemini-2.5-flash-lite

    often beyond possibly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    ステル
    0.49
    icherweise
    0.46
     cinquième
    0.46
     Сасик
    0.46
    BeerItem
    0.46
     ۴
    0.45
    ChooseServer
    0.45
    чня
    0.45
     آدمی
    0.44
    electrons
    0.44
    POSITIVE LOGITS
    মো
    0.51
     indexes
    0.49
     markers
    0.49
     shields
    0.47
    보
    0.47
     teammates
    0.47
    안
    0.47
    體
    0.47
    팀
    0.47
    대
    0.46
    Activations Density 0.000%

    No Known Activations