© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187203
    Prev
    Next
    INDEX
    Explanations

    qualities, names, times, emotions, distance, companies, lives, conditions

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

    as it's easier

    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
    Negative Logits
     ا
    0.47
     Trieste
    0.47
     এ
    0.46
     beim
    0.46
     Venice
    0.45
     generell
    0.45
     wales
    0.44
     オレンジ
    0.44
     Norway
    0.42
     gutes
    0.42
    POSITIVE LOGITS
    だけど
    0.47
    Cooldown
    0.47
     мора
    0.46
    Wage
    0.45
    сім
    0.44
    КУ
    0.44
    ुणा
    0.42
    丈
    0.42
    χη
    0.41
    극한
    0.41
    Activations Density 0.001%

    No Known Activations