© 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. 192255
    Prev
    Next
    INDEX
    Explanations

    locations, quantities, and status

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

    test and intended actions

    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
     宋
    0.53
     ರಚ
    0.48
     ಪುಸ್ತಕ
    0.48
     улице
    0.47
     fatores
    0.46
     εισ
    0.46
     iskol
    0.46
     大家
    0.46
     respuestas
    0.45
     விளையாட்டு
    0.45
    POSITIVE LOGITS
    p
    0.54
    mix
    0.45
    و
    0.45
    淹
    0.44
    斤
    0.43
    collage
    0.43
    meng
    0.42
    axes
    0.42
    roon
    0.42
    2
    0.42
    Activations Density 0.001%

    No Known Activations