© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29471
    Prev
    Next
    INDEX
    Explanations

    chain reaction

    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_40_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
    orthodox
    0.41
    ਾਕ
    0.40
    涀
    0.39
    crs
    0.37
     orthogonal
    0.37
     कां
    0.37
    cdZ
    0.36
    }-\
    0.36
    /-
    0.36
    Equatable
    0.36
    POSITIVE LOGITS
     Harp
    0.46
    笞
    0.46
     harp
    0.44
     patio
    0.43
     garnish
    0.41
     ужа
    0.41
     embankment
    0.39
     patios
    0.39
    璫
    0.39
     gage
    0.38
    Activations Density 0.000%

    No Known Activations