© 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. 54250
    Prev
    Next
    INDEX
    Explanations

    geometric descriptions and documentation

    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
    ēt
    0.49
     Theor
    0.46
    ellt
    0.45
    Kar
    0.44
     lack
    0.43
    Bur
    0.43
     Burberry
    0.43
    ر
    0.43
    bur
    0.42
     la
    0.42
    POSITIVE LOGITS
    modifiers
    0.46
     আমরা
    0.46
     Localization
    0.43
     приме
    0.43
    sourcePort
    0.43
    keyDown
    0.43
     কম্প
    0.43
    cB
    0.42
    旣
    0.42
    ingredients
    0.42
    Activations Density 0.001%

    No Known Activations