© 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. 213149
    Prev
    Next
    INDEX
    Explanations

    preceding or following words

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

    capture the essence

    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
    UILLER
    0.52
    வும்
    0.50
    ਰ
    0.50
     മരണ
    0.47
     VOL
    0.46
     topography
    0.46
    OSED
    0.45
    вший
    0.44
    対流
    0.44
    REETYPE
    0.43
    POSITIVE LOGITS
    end
    0.53
     escul
    0.53
    fy
    0.49
    ovi
    0.48
    ular
    0.46
    8
    0.46
    ight
    0.46
    ned
    0.46
    JavaScript
    0.45
    H
    0.45
    Activations Density 0.000%

    No Known Activations