© 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. 226
    Prev
    Next
    INDEX
    Explanations

    Analysis, supplier, rights, songs, coupons, me

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

    time and improvements

    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
    ల్యే
    0.40
     mêmes
    0.36
    roffenen
    0.36
     වශ
    0.36
    ﺘ
    0.36
     Komponenten
    0.36
     Haven
    0.35
     właśnie
    0.35
    সরকারী
    0.35
     sogenannten
    0.34
    POSITIVE LOGITS
    0.35
    As
    0.34
     unfolds
    0.34
     (
    0.33
    AN
    0.33
    you
    0.33
    poses
    0.33
    nows
    0.33
     huwa
    0.33
    Occupation
    0.33
    Activations Density 0.394%

    No Known Activations