© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192662
    Prev
    Next
    INDEX
    Explanations

    describing specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </bbox>
    0.41
    ینے
    0.40
    每一個
    0.39
     habitantes
    0.39
    ەند
    0.39
    インストール
    0.38
    ếc
    0.38
     kingdom
    0.38
     émissions
    0.38
    approved
    0.37
    POSITIVE LOGITS
    ♉
    0.41
     Philosophical
    0.40
    oreal
    0.40
     Kommentar
    0.39
     Des
    0.39
     Comment
    0.39
    yar
    0.39
    osov
    0.37
     Terbaru
    0.37
    ningar
    0.37
    Activations Density 0.001%

    No Known Activations