© 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. 171943
    Prev
    Next
    INDEX
    Explanations

    pointer to structure

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

    checking object types

    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
    LuaPush
    0.46
    ाराम
    0.44
    ಾಯಿತು
    0.42
    ͓
    0.41
    Raquete
    0.40
    ьев
    0.40
    치를
    0.39
    meisterschaft
    0.39
     قانونی
    0.39
     vente
    0.39
    POSITIVE LOGITS
    )?.
    0.37
     شناخته
    0.37
     kahe
    0.37
    rz
    0.37
    丙
    0.37
     cụ
    0.36
    ETTE
    0.36
     intellect
    0.35
     subtype
    0.35
     Elderly
    0.35
    Activations Density 0.004%

    No Known Activations