© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32838
    Prev
    Next
    INDEX
    Explanations

    just got

    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_16_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
    ینګ
    0.57
    сійскай
    0.54
    Void
    0.52
     gerade
    0.51
    যদি
    0.49
    ennzeichnet
    0.49
    ^{-
    0.48
    trashItem
    0.48
    基本的に
    0.48
    ूला
    0.48
    POSITIVE LOGITS
     I
    0.61
     Z
    0.59
     the
    0.56
     bursts
    0.54
     combats
    0.52
     Collectors
    0.50
    er
    0.49
     A
    0.49
     a
    0.49
     N
    0.49
    Activations Density 0.000%

    No Known Activations