© 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. 198814
    Prev
    Next
    INDEX
    Explanations

    describing states or qualities

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

    definition and qualification

    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
    说
    0.49
    ए
    0.48
     рекоменду
    0.48
    ಬ
    0.47
    華
    0.47
     рекоменда
    0.46
    HTC
    0.46
    える
    0.46
     disponível
    0.46
    Ę
    0.46
    POSITIVE LOGITS
    fer
    0.44
    urrection
    0.43
    ufficient
    0.41
    gender
    0.41
     peur
    0.40
     chau
    0.40
     repertoire
    0.39
    انى
    0.39
     parfait
    0.39
     voisinage
    0.39
    Activations Density 0.002%

    No Known Activations