© 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. 47518
    Prev
    Next
    INDEX
    Explanations

    proportional relationships and dependencies

    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
    iyesi
    0.42
    HPO
    0.39
    rasi
    0.39
     retry
    0.38
    VIDOR
    0.37
    =[];
    0.37
    áng
    0.37
    ujemy
    0.36
     zaken
    0.36
    ágot
    0.36
    POSITIVE LOGITS
    bathroom
    0.45
     lodging
    0.45
    präsident
    0.44
     periódico
    0.44
    카드
    0.43
     Пар
    0.42
    ير
    0.41
     וו
    0.41
     cardiop
    0.41
    遢
    0.40
    Activations Density 0.003%

    No Known Activations