© 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. 35460
    Prev
    Next
    INDEX
    Explanations

    parsing integers and reading data

    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
    莨
    0.40
    哺乳
    0.38
    RawO
    0.37
     ধারে
    0.36
     பள்ள
    0.36
    檔
    0.36
    部に
    0.35
     punctato
    0.35
    冶
    0.35
    இந்
    0.35
    POSITIVE LOGITS
    Nullable
    0.59
     reader
    0.54
     readers
    0.54
    Reader
    0.50
    dr
    0.47
    readers
    0.47
    reader
    0.46
     Reader
    0.46
     dr
    0.45
     Drilling
    0.42
    Activations Density 0.008%

    No Known Activations