© 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. 64095
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    systems, outlets, freeze, however, scale

    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
    umuz
    0.56
    awang
    0.51
    აზე
    0.51
     택
    0.50
    ąc
    0.50
     şek
    0.49
     대상
    0.49
     የበለጠ
    0.49
    entesque
    0.48
    ęć
    0.48
    POSITIVE LOGITS
     which
    0.52
    Some
    0.50
    which
    0.47
    初期
    0.45
    Which
    0.45
    ซึ่ง
    0.44
    書籍
    0.42
    關於
    0.42
    欱
    0.42
     amely
    0.41
    Activations Density 0.000%

    No Known Activations