© 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. 4547
    Prev
    Next
    INDEX
    Explanations

    foreign words and numbers

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

    numbers and quantities

    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
    ↵↵
    0.56
    ط
    0.56
    ↵
    0.54
     N
    0.54
     CGI
    0.51
    iniu
    0.51
     Compact
    0.51
     Ni
    0.50
    ص
    0.50
    af
    0.50
    POSITIVE LOGITS
     drove
    0.55
     ಕಳೆದ
    0.55
     ಖರೀ
    0.54
    コミュニ
    0.53
     ಆದರೆ
    0.52
     coordonnées
    0.52
    ೧
    0.52
     paymentRequest
    0.51
     ഒഴി
    0.50
     ಕೇಂದ್ರ
    0.49
    Activations Density 0.000%

    No Known Activations