© 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-65K
    7. 46715
    Prev
    Next
    INDEX
    Explanations

    router and navigation

    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_65k_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
     ಯಾವ
    0.47
     фестива
    0.46
    農業
    0.45
     주제
    0.45
    ऩ
    0.45
     시간에는
    0.44
    темати
    0.44
    釟
    0.44
    侙
    0.44
     પ્રવેશ
    0.43
    POSITIVE LOGITS
     using
    0.49
     Sonic
    0.46
     ammonium
    0.44
    Type
    0.43
    Sonic
    0.42
     installation
    0.41
     sonic
    0.41
    6
    0.40
     rocket
    0.40
     version
    0.40
    Activations Density 0.010%

    No Known Activations