© 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. 186773
    Prev
    Next
    INDEX
    Explanations

    non-english or specialized terms

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

    recent years

    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
    Digital
    0.47
    女儿
    0.47
     디지털
    0.47
    ลูก
    0.45
     Digital
    0.44
    ?}
    0.43
     แยก
    0.43
    茼
    0.42
    Join
    0.42
    คุณ
    0.42
    POSITIVE LOGITS
     آسان
    0.53
    cooked
    0.52
    newdata
    0.52
    avgs
    0.52
     تفس
    0.50
    methods
    0.49
     métodos
    0.49
    outof
    0.48
    fromParams
    0.48
     طبی
    0.48
    Activations Density 0.000%

    No Known Activations