© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101537
    Prev
    Next
    INDEX
    Explanations

    automotive manufacturers, light therapy, equities

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

    held aloft

    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
    `
    0.47
    --
    0.46
     tad
    0.46
    ’
    0.45
    alka
    0.45
     chlorides
    0.45
    '
    0.44
     gelen
    0.44
     resources
    0.43
     cref
    0.43
    POSITIVE LOGITS
    舜
    0.49
    成長
    0.48
    зіно
    0.46
    の写真
    0.46
    逓
    0.44
    ЕМ
    0.44
    лед
    0.43
    е
    0.43
    )}+\
    0.43
    ун
    0.43
    Activations Density 0.000%

    No Known Activations