© 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. 143322
    Prev
    Next
    INDEX
    Explanations

    questions about suitability

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

    than training or smaller models

    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
    ಡುವುದ
    0.49
    Dumper
    0.46
    ∨
    0.45
    Loss
    0.43
    予以
    0.43
    BrNO
    0.43
    ゞ
    0.42
     seriously
    0.42
     traitor
    0.42
    ╽
    0.42
    POSITIVE LOGITS
     ugy
    0.52
    7
    0.52
     rendelkez
    0.51
    agan
    0.50
    ipa
    0.48
    ouv
    0.48
    .',
    0.47
    iew
    0.46
    utan
    0.46
    undaki
    0.46
    Activations Density 0.001%

    No Known Activations