© 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. 176056
    Prev
    Next
    INDEX
    Explanations

    followed by where

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

    suffixes indicating information

    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
    н
    0.48
    حاد
    0.47
    િ
    0.46
    р
    0.46
    收入
    0.45
    ант
    0.45
    خواه
    0.45
    лом
    0.44
    Luke
    0.44
    ه
    0.44
    POSITIVE LOGITS
     Jeju
    0.60
     bleached
    0.56
     RoHS
    0.54
     ブランド
    0.53
     โอ
    0.53
     wygl
    0.53
     バス
    0.51
     ASH
    0.50
     unveils
    0.50
     zez
    0.49
    Activations Density 0.000%

    No Known Activations