© 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. 205249
    Prev
    Next
    INDEX
    Explanations

    seller location

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

    household items and biological terms

    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
    a
    0.46
     Tread
    0.45
    ╠
    0.45
     தெரிவித்தனர்
    0.45
    {}".
    0.44
     DataSource
    0.44
     rechts
    0.43
     Toby
    0.43
    谊
    0.43
    сер
    0.42
    POSITIVE LOGITS
     conforms
    0.47
     chores
    0.44
     clings
    0.43
     ગઈ
    0.42
     radiographs
    0.42
     clothing
    0.42
     snowboarding
    0.41
     obeys
    0.41
     movies
    0.40
     homology
    0.40
    Activations Density 0.001%

    No Known Activations