© 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. 142043
    Prev
    Next
    INDEX
    Explanations

    basis for decisions and actions

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

    . HER vs OER

    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
     orbits
    0.55
     URLs
    0.53
    ेंटीना
    0.52
     arrang
    0.49
     Volumes
    0.49
    🕹
    0.47
     Xét
    0.47
    ार्क
    0.46
    ᠴ
    0.46
     internazionali
    0.46
    POSITIVE LOGITS
    op
    0.57
    il
    0.50
    isil
    0.48
     ph
    0.46
    odem
    0.46
    roep
    0.45
    alpha
    0.44
    o
    0.43
    inic
    0.43
    end
    0.43
    Activations Density 0.000%

    No Known Activations