© 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. 31-GEMMASCOPE-2-RES-262K
    7. 201300
    Prev
    Next
    INDEX
    Explanations

    functions, math, and specific examples

    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
     बनाया
    0.52
    σα
    0.52
     ぐらい
    0.52
    𝐜
    0.52
     因为
    0.49
     disminución
    0.49
    čia
    0.49
    𝐥
    0.48
     可愛
    0.48
     llevando
    0.48
    POSITIVE LOGITS
     FUNC
    0.43
     vent
    0.43
     ts
    0.42
     sword
    0.42
     clav
    0.42
     SPE
    0.41
     mol
    0.41
     PROP
    0.41
     ناف
    0.41
     sich
    0.40
    Activations Density 0.000%

    No Known Activations