© 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. 168930
    Prev
    Next
    INDEX
    Explanations

    spacetime, port, or `can` discussing topics

    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
    ORITY
    0.41
     survival
    0.40
    }-(
    0.40
    或其他
    0.39
     white
    0.38
     survived
    0.38
    Brush
    0.38
    Subsection
    0.38
    Phone
    0.38
     ឬ
    0.37
    POSITIVE LOGITS
     পারবেন
    0.41
    २०
    0.41
     vars
    0.39
    gc
    0.38
     gelecek
    0.38
     التى
    0.38
     dunno
    0.38
     পারেন
    0.37
    ཿ
    0.37
    wot
    0.36
    Activations Density 0.003%

    No Known Activations