© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213754
    Prev
    Next
    INDEX
    Explanations

    finish, restart, extract, lost

    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
    allowing
    0.37
     komunik
    0.36
     allowing
    0.35
     bs
    0.35
     በማ
    0.35
    墀
    0.35
     GSK
    0.34
     alertas
    0.34
     tema
    0.34
     realización
    0.34
    POSITIVE LOGITS
     finished
    0.42
    finish
    0.41
     finish
    0.39
    ジネス
    0.39
    Finish
    0.38
     Finished
    0.38
    浊
    0.37
     Finish
    0.37
     શરૂ
    0.35
    restart
    0.35
    Activations Density 0.106%

    No Known Activations