© 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. 1813
    Prev
    Next
    INDEX
    Explanations

    except these

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

    pointers to specific items or actions

    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
    สำหรับการ
    0.34
    那我
    0.33
    𝟏
    0.33
    ཧ
    0.31
     எனக்கு
    0.31
    avigation
    0.30
     궁금
    0.30
    𝟭
    0.29
    serious
    0.29
     unequivocal
    0.29
    POSITIVE LOGITS
     this
    0.77
     tohoto
    0.66
     této
    0.64
     these
    0.64
     aceste
    0.64
     этих
    0.63
     этой
    0.62
     dieser
    0.61
     acest
    0.61
     tejto
    0.61
    Activations Density 0.527%

    No Known Activations