© 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. 6109
    Prev
    Next
    INDEX
    Explanations

    アンダーフィル剤

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

    transliterations and foreign words

    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
    iva
    0.35
    ‚
    0.35
    an
    0.33
    őbb
    0.32
    ло
    0.31
    isOn
    0.31
     п
    0.31
    ть
    0.31
     ،
    0.31
    un
    0.30
    POSITIVE LOGITS
    ・
    0.38
    ：
    0.37
    ↵
    0.36
    メージ
    0.34
    เตอร์
    0.33
    ッジ
    0.33
     interfere
    0.32
    ー
    0.31
     asymptotically
    0.31
    ティ
    0.30
    Activations Density 0.026%

    No Known Activations