© 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. 221775
    Prev
    Next
    INDEX
    Explanations

    slack messages and channels

    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
    _{{\
    0.43
    (),"
    0.38
     robotic
    0.38
     robot
    0.37
     asleep
    0.37
    web
    0.37
     ";
    0.37
    echolog
    0.37
     console
    0.36
    爱的
    0.36
    POSITIVE LOGITS
    Rut
    0.42
     Corrections
    0.41
    Ꮫ
    0.40
    魉
    0.40
    YP
    0.39
    کو
    0.38
    Bulk
    0.38
    Tobacco
    0.38
    Tax
    0.38
     للع
    0.38
    Activations Density 0.001%

    No Known Activations