© 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. 28880
    Prev
    Next
    INDEX
    Explanations

    investigative, owners, hose, biggest

    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
     decor
    0.43
     e
    0.41
    miss
    0.41
    黄
    0.41
    Mehr
    0.40
    전
    0.40
    大
    0.40
    庫
    0.39
    คุณ
    0.38
    mtable
    0.38
    POSITIVE LOGITS
    찬가지
    0.53
     акчага
    0.52
    INFRINGEMENT
    0.52
     Quadrupèdes
    0.51
     けど
    0.50
    ”،
    0.50
    ।*
    0.49
    PIA
    0.49
    trashItem
    0.48
     bhfu
    0.48
    Activations Density 0.003%

    No Known Activations