© 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-65K
    7. 14827
    Prev
    Next
    INDEX
    Explanations

    4k 60hz

    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
     favorita
    0.43
     spectacularly
    0.40
     ciertos
    0.39
     bò
    0.39
     quarterback
    0.38
     Chipotle
    0.38
    '>{
    0.38
     التص
    0.38
    andowski
    0.38
    蟋
    0.38
    POSITIVE LOGITS
    spread
    0.52
    레이
    0.46
    ບບ
    0.46
    气
    0.45
     figures
    0.45
    sustaining
    0.45
    EX
    0.44
    톤
    0.44
     Ton
    0.44
    Ton
    0.44
    Activations Density 0.008%

    No Known Activations