© 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. 31-GEMMASCOPE-2-RES-262K
    7. 93926
    Prev
    Next
    INDEX
    Explanations

    early treatment

    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
     harbor
    0.48
    joining
    0.46
    ytocin
    0.46
    -
    0.46
    actual
    0.45
    യ്‌
    0.44
     play
    0.44
     ball
    0.43
    ulins
    0.42
    ball
    0.41
    POSITIVE LOGITS
    兟
    0.60
    स्स
    0.50
    簟
    0.49
     Idam
    0.48
     atteint
    0.47
     بعدها
    0.46
     Theories
    0.46
     Ordering
    0.46
    妷
    0.45
     المنتج
    0.45
    Activations Density 0.000%

    No Known Activations