© 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. 88306
    Prev
    Next
    INDEX
    Explanations

    maximum of, absent a, want to

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

    examples and definitions

    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
    ون
    0.57
    י
    0.54
    ي
    0.54
    UD
    0.53
    ud
    0.49
    D
    0.49
    s
    0.47
    ด
    0.46
    in
    0.45
    م
    0.43
    POSITIVE LOGITS
     लंबा
    0.46
     Definition
    0.45
    伝え
    0.44
     gesprochen
    0.43
     Girona
    0.43
    რძ
    0.43
    ນິກ
    0.43
     Bezeichnung
    0.42
     முதல்
    0.41
     JsonResult
    0.41
    Activations Density 0.000%

    No Known Activations