© 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. 192299
    Prev
    Next
    INDEX
    Explanations

    foreign words and punctuation

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

    store-bought convenience

    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
    Rồi
    0.57
    蕴
    0.51
    ᥣ
    0.50
    第壹百
    0.50
    TRR
    0.50
     вновь
    0.49
     resolves
    0.47
    nac
    0.46
    ᥒ
    0.46
     Bildern
    0.45
    POSITIVE LOGITS
     megap
    0.47
    -
    0.44
     رب
    0.43
    Expense
    0.43
     أساس
    0.43
     professional
    0.42
     Circ
    0.42
    Expressions
    0.42
     mec
    0.42
    寿命
    0.41
    Activations Density 0.000%

    No Known Activations