© 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. 26533
    Prev
    Next
    INDEX
    Explanations

    mathematical number systems

    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
    essence
    0.39
    乘客
    0.39
    蒂
    0.38
    uru
    0.38
    ace
    0.37
     manta
    0.37
    pron
    0.37
    unsubscribe
    0.37
    客户
    0.37
    ounc
    0.37
    POSITIVE LOGITS
     integers
    0.80
     integer
    0.75
    Integer
    0.73
     Integer
    0.73
    整数
    0.71
    ℤ
    0.68
    INTEGER
    0.66
    integer
    0.60
     Inte
    0.56
    ℕ
    0.56
    Activations Density 0.009%

    No Known Activations