© 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-262K
    7. 90668
    Prev
    Next
    INDEX
    Explanations

    programming examples or explanations

    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_262k_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
    та
    0.45
    지
    0.43
     needs
    0.43
    вы
    0.41
     прод
    0.39
     constantly
    0.39
     journey
    0.39
    зна
    0.39
    сто
    0.38
    とは
    0.38
    POSITIVE LOGITS
    <0xD5>
    0.54
     Dodgers
    0.53
     olefins
    0.52
     wodurch
    0.52
    ⌝
    0.51
     inferred
    0.50
     concess
    0.50
    icklabels
    0.50
     Nexon
    0.50
    ట్స్‌
    0.49
    Activations Density 0.006%

    No Known Activations