© 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. 153020
    Prev
    Next
    INDEX
    Explanations

    additional information or items

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

    based on

    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
     yǒu
    0.52
     Texas
    0.49
     Texans
    0.48
     学校
    0.46
     Californians
    0.46
     Ét
    0.45
     Sénégal
    0.45
     plantes
    0.44
     内
    0.43
    consulté
    0.43
    POSITIVE LOGITS
     tambahan
    0.47
     antal
    0.45
    ispo
    0.42
     adicionales
    0.40
     дополнительных
    0.40
    فضل
    0.39
    સાર
    0.39
     sepanjang
    0.39
     zusätzliche
    0.39
    ystyle
    0.39
    Activations Density 0.000%

    No Known Activations