© 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. 51701
    Prev
    Next
    INDEX
    Explanations

    contrast exceptions concessions

    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
    FULLY
    0.46
     Größen
    0.43
    高齢
    0.40
     pamoja
    0.40
     koordin
    0.39
    合わせた
    0.39
    EMANN
    0.39
    √
    0.39
    ろう
    0.39
    ходя
    0.38
    POSITIVE LOGITS
     urinary
    0.49
     시
    0.49
     worthwhile
    0.49
     Fairchild
    0.48
     identical
    0.48
     nuisance
    0.48
     Sanger
    0.47
     culpa
    0.47
    forschungs
    0.46
     Amaya
    0.46
    Activations Density 0.002%

    No Known Activations