© 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. 123466
    Prev
    Next
    INDEX
    Explanations

    decision status exclusion

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

    tells the other parts

    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
    𒁉
    0.51
     そんな
    0.47
     భాష
    0.47
    езде
    0.47
     พวก
    0.46
     ቅር
    0.46
     Warsz
    0.45
     семья
    0.45
    rbrakk
    0.45
     아주
    0.45
    POSITIVE LOGITS
    聞
    0.45
    如果是
    0.44
    置
    0.43
    decision
    0.41
     decision
    0.40
     Exclusion
    0.40
    下一步
    0.40
    旁
    0.40
    status
    0.39
    K
    0.39
    Activations Density 0.006%

    No Known Activations