© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82627
    Prev
    Next
    INDEX
    Explanations

    class-action request codes current

    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_31_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
     cryptic
    0.50
     techo
    0.47
     goof
    0.46
     tinker
    0.45
     obscure
    0.44
    <0xE3>
    0.44
     laying
    0.43
    મ
    0.43
     Galaxy
    0.42
    பு
    0.42
    POSITIVE LOGITS
    िलास
    0.46
    rijving
    0.46
    irling
    0.46
    ielt
    0.46
    teras
    0.45
    ("|"+"
    0.45
    ]^{-
    0.43
    gelt
    0.43
    inger
    0.43
     ವ್ಯಾ
    0.43
    Activations Density 0.000%

    No Known Activations