© 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. 12318
    Prev
    Next
    INDEX
    Explanations

    signed and unsigned integer types

    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
    parseDouble
    0.47
    parseFloat
    0.43
    ubmit
    0.43
     متش
    0.41
    ^{(\
    0.41
     नमी
    0.40
    ]={"
    0.40
    }({\
    0.39
     palace
    0.39
     भूल
    0.39
    POSITIVE LOGITS
     sizes
    0.81
     size
    0.80
     signed
    0.80
     unsigned
    0.79
     Signed
    0.75
     sized
    0.74
    size
    0.69
    サイズ
    0.68
     Sizes
    0.66
    Signed
    0.66
    Activations Density 0.021%

    No Known Activations