© 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. 176189
    Prev
    Next
    INDEX
    Explanations

    selection and choice

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

    round glasses

    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
    臾
    0.52
    ادرات
    0.50
    匯
    0.50
     collectively
    0.49
    িন
    0.49
    我們會
    0.48
    我們
    0.46
    叡
    0.45
    ემ
    0.45
    ሰ
    0.45
    POSITIVE LOGITS
     ().
    0.54
     personaje
    0.47
     (),
    0.46
     dhammo
    0.46
     প্রস্তাবে
    0.45
     aunque
    0.44
     penyebab
    0.44
     IUser
    0.44
     alleles
    0.44
     amu
    0.44
    Activations Density 0.002%

    No Known Activations