© 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. 228265
    Prev
    Next
    INDEX
    Explanations

    signed proof lifetime

    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
    กรรม
    0.46
    ვა
    0.46
     Fluor
    0.45
    MNumber
    0.45
    ツー
    0.45
     }:
    0.44
    タ
    0.43
     শুকনো
    0.42
    detection
    0.42
    いません
    0.42
    POSITIVE LOGITS
     sees
    0.49
     saw
    0.47
    е
    0.46
     recompens
    0.45
     видеть
    0.44
     finner
    0.44
    .).
    0.43
    verting
    0.43
     봤
    0.42
     magn
    0.42
    Activations Density 0.000%

    No Known Activations