© 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. 62885
    Prev
    Next
    INDEX
    Explanations

    at parties, emojis to, LinkedIn -

    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
     hipótesis
    0.48
    萦
    0.47
    ღვ
    0.47
    isetas
    0.45
    züge
    0.45
    告訴
    0.43
     começou
    0.43
    考えると
    0.42
     Brésil
    0.42
    িট
    0.42
    POSITIVE LOGITS
    杜
    0.46
    umer
    0.44
     outcry
    0.44
     thousand
    0.42
     vernacular
    0.42
     ditch
    0.42
     lakh
    0.41
     ordeal
    0.41
     yıll
    0.41
    াদিগকে
    0.41
    Activations Density 0.001%

    No Known Activations