© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235480
    Prev
    Next
    INDEX
    Explanations

    round Sunday future

    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
    Negative Logits
    ที่จะ
    0.48
    งาน
    0.44
    拳
    0.44
    underwear
    0.43
    lok
    0.42
    𝗜
    0.42
    TypeText
    0.41
     типу
    0.40
    ที่ไม่
    0.40
    ጡ
    0.40
    POSITIVE LOGITS
    大部分
    0.51
     poco
    0.45
     habíamos
    0.44
    也都
    0.43
     pouco
    0.42
     dB
    0.41
     H
    0.41
     Prolong
    0.41
     prolonged
    0.41
     casi
    0.41
    Activations Density 0.000%

    No Known Activations