© 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-16K
    7. 8237
    Prev
    Next
    INDEX
    Explanations

    type casting and conversions

    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_16k_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
     isolating
    0.42
    meas
    0.39
     `=`,
    0.36
    測
    0.36
     மாய
    0.36
    measurement
    0.35
    ביע
    0.35
    抵
    0.35
     mala
    0.35
    pointee
    0.35
    POSITIVE LOGITS
     cast
    1.11
     Cast
    1.09
     casts
    1.00
    cast
    0.98
     कास्ट
    0.96
    Cast
    0.95
     CAST
    0.95
     casting
    0.94
     Casting
    0.93
    CAST
    0.88
    Activations Density 0.113%

    No Known Activations