© 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. 145092
    Prev
    Next
    INDEX
    Explanations

    steel pipe distributors

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

    roles and tasks

    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
    Performing
    0.50
    κέ
    0.48
    uffix
    0.46
    彎
    0.46
     చక్కెర
    0.46
    نية
    0.46
    Resol
    0.46
    𝗢
    0.45
    മ്പ്
    0.45
    雅黑
    0.45
    POSITIVE LOGITS
    w
    0.53
     CRS
    0.49
    ра
    0.47
     contaminated
    0.46
     resulted
    0.46
    ́ng
    0.46
     are
    0.45
     ра
    0.45
     tainted
    0.45
    CRS
    0.45
    Activations Density 0.001%

    No Known Activations