© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 43879
    Prev
    Next
    INDEX
    Explanations

    list items

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

    analysis algorithm chain equations product opposite sum while

    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
    প্ট
    0.46
    是一些
    0.45
    MathClass
    0.43
    init
    0.43
    compressible
    0.43
    implement
    0.42
    ὕ
    0.42
    Beyblade
    0.41
    increased
    0.41
    this
    0.41
    POSITIVE LOGITS
     이를
    0.48
    专家
    0.47
     शुल्क
    0.46
     женой
    0.45
     남
    0.45
     തുറ
    0.45
    官员
    0.44
     указыва
    0.44
     전문가
    0.43
     服务
    0.43
    Activations Density 0.000%

    No Known Activations