© 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-262K
    7. 83610
    Prev
    Next
    INDEX
    Explanations

    time or history

    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
    情绪
    0.47
     eterno
    0.46
     inevitably
    0.46
     immigrated
    0.45
    恻
    0.45
    原则
    0.44
    ोग्राम
    0.43
     eternally
    0.43
     unequivocally
    0.42
     invariably
    0.41
    POSITIVE LOGITS
    9
    0.56
    a
    0.55
    8
    0.53
    3
    0.51
    austral
    0.49
    resistant
    0.49
     t
    0.47
    5
    0.47
    soph
    0.46
     ت
    0.46
    Activations Density 0.008%

    No Known Activations