© 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. 92172
    Prev
    Next
    INDEX
    Explanations

    risk of development

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

    Personal preferences or specific topics

    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
     書い
    0.50
     bustling
    0.49
     ডেভেলপ
    0.49
    transfected
    0.48
     両
    0.47
    \}$,
    0.47
     nt
    0.46
     passed
    0.46
     snippets
    0.46
     jokingly
    0.46
    POSITIVE LOGITS
    เป็นการ
    0.47
    isés
    0.45
    సాగ
    0.45
    an
    0.45
    Adding
    0.45
    填
    0.45
    ichtigung
    0.44
     humide
    0.44
    Minimum
    0.43
    сово
    0.42
    Activations Density 0.000%

    No Known Activations