© 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. 134848
    Prev
    Next
    INDEX
    Explanations

    leading brands and products

    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
     indium
    0.59
     //<
    0.55
     itd
    0.54
    മല
    0.49
     hablan
    0.49
     företag
    0.49
     indust
    0.48
     endothelial
    0.48
     ɖ
    0.48
    𒆠
    0.48
    POSITIVE LOGITS
    绪
    0.46
    rzy
    0.45
    wicz
    0.44
    ọng
    0.44
    ttle
    0.44
    胸
    0.44
    兄弟
    0.43
    ời
    0.43
    震
    0.42
    未必
    0.42
    Activations Density 0.000%

    No Known Activations