© 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. 153421
    Prev
    Next
    INDEX
    Explanations

    directly

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

    lack of suitability or association

    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
    ؟
    0.56
     tools
    0.48
     Zaragoza
    0.46
     lipids
    0.46
     leukocyte
    0.45
     hematopoietic
    0.45
     equipo
    0.44
     peaks
    0.43
     logarithms
    0.43
     proteins
    0.43
    POSITIVE LOGITS
    可以直接
    0.50
    直接
    0.47
    現實
    0.46
    쉽
    0.46
    䘚
    0.46
    🚢
    0.45
    այր
    0.43
    洒
    0.43
    有り
    0.43
    前
    0.43
    Activations Density 0.002%

    No Known Activations