© 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. 45096
    Prev
    Next
    INDEX
    Explanations

    specifies what something is

    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
     чувства
    0.47
    戏剧
    0.46
    危机
    0.45
    读书
    0.44
     الق
    0.44
     кризи
    0.44
    幵
    0.44
    梦想
    0.43
    谋
    0.42
    शिक्षा
    0.42
    POSITIVE LOGITS
    subseteq
    0.45
     specifying
    0.43
    wasm
    0.43
     specifies
    0.42
     originated
    0.42
    identifier
    0.41
     TeV
    0.41
     extends
    0.41
    provides
    0.41
     classifies
    0.41
    Activations Density 0.007%

    No Known Activations