© 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. 40-GEMMASCOPE-2-RES-262K
    7. 34452
    Prev
    Next
    INDEX
    Explanations

    using programming concepts

    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
    Ukrainian
    0.39
    𝓙
    0.39
    nemidophorus
    0.39
    粗
    0.39
    mittel
    0.39
    欧美
    0.38
     للنساء
    0.38
    ampoo
    0.38
     profinite
    0.38
    ﻀ
    0.37
    POSITIVE LOGITS
     Sou
    0.48
     Erosion
    0.40
     Events
    0.39
     entering
    0.39
     조
    0.38
     provision
    0.38
     Leave
    0.38
     Fam
    0.38
     Plush
    0.38
     Provision
    0.38
    Activations Density 0.000%

    No Known Activations