© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 84966
    Prev
    Next
    INDEX
    Explanations

    NVIDIA, analysis, minutes

    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
     No
    0.41
     PK
    0.38
    력
    0.38
    磵
    0.38
     Corn
    0.38
    使用
    0.38
     Yu
    0.37
    ழ
    0.37
     Poll
    0.36
    No
    0.36
    POSITIVE LOGITS
    reserved
    0.43
    tted
    0.42
    inactive
    0.41
    රි
    0.41
    reliability
    0.38
    roč
    0.38
     ottimo
    0.38
    onics
    0.37
    excellent
    0.37
     brushing
    0.37
    Activations Density 0.000%

    No Known Activations