© 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. 50244
    Prev
    Next
    INDEX
    Explanations

    projection onto a plane

    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
    绾
    0.46
    綰
    0.46
     thefts
    0.43
    ኰ
    0.42
     кет
    0.41
    నా
    0.41
    バッグ
    0.39
     loadings
    0.38
    лец
    0.38
    ConsoleText
    0.38
    POSITIVE LOGITS
     Netflix
    0.58
     or
    0.46
     Russia
    0.44
     geopol
    0.43
     South
    0.43
    /
    0.43
     on
    0.43
     Trump
    0.42
     Ukraine
    0.41
     Department
    0.41
    Activations Density 0.002%

    No Known Activations