© 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. 243501
    Prev
    Next
    INDEX
    Explanations

    replacement or comparison

    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
    אם
    0.49
    墓
    0.49
    اك
    0.44
    宗
    0.44
     MainForm
    0.44
    ◤
    0.43
    ادة
    0.43
    ０
    0.43
    شب
    0.42
    টা
    0.42
    POSITIVE LOGITS
    str
    0.57
    ref
    0.52
    say
    0.52
    jej
    0.50
    esthetic
    0.50
    replace
    0.50
     another
    0.49
     aar
    0.49
     admittedly
    0.49
    lymph
    0.49
    Activations Density 0.000%

    No Known Activations