© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80322
    Prev
    Next
    INDEX
    Explanations

    specific word pairings following keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    specific terms followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ।
    0.54
    )।
    0.48
     but
    0.46
     Edd
    0.46
     dell
    0.45
    াকা
    0.44
    veland
    0.44
     in
    0.43
     of
    0.43
    ق
    0.43
    POSITIVE LOGITS
    erosion
    0.54
    serverResponse
    0.52
    ▥
    0.47
     தொலைக்காட்சி
    0.47
    buildCommand
    0.46
    ческом
    0.46
     cuisson
    0.46
    approximation
    0.45
    Picklist
    0.45
    accuracy
    0.44
    Activations Density 0.000%

    No Known Activations