© 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. 23072
    Prev
    Next
    INDEX
    Explanations

    web pages, matrix, signals, space

    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
    iota
    0.48
    ol
    0.41
    ipart
    0.41
    pi
    0.41
    times
    0.40
    enumi
    0.39
    rceil
    0.38
     %
    0.38
    epsilon
    0.38
    c
    0.37
    POSITIVE LOGITS
    }{$\
    0.48
    শাসন
    0.45
    }{$
    0.43
    Semitism
    0.43
    рисо
    0.43
     চৌধুরী
    0.42
    يمه
    0.42
    )}}{
    0.42
    μον
    0.42
    ","$
    0.42
    Activations Density 0.000%

    No Known Activations