© 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. 25000
    Prev
    Next
    INDEX
    Explanations

    Python class initialization

    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
    h
    0.58
    0.57
    ↵
    0.51
     $
    0.50
     Pixel
    0.49
     would
    0.48
    ing
    0.47
     can
    0.46
     will
    0.45
     Workout
    0.45
    POSITIVE LOGITS
    ב
    0.54
    ব
    0.49
    然後
    0.43
    semanticweb
    0.43
    ám
    0.42
    ége
    0.42
    spaces
    0.41
    ุน
    0.41
    𝒐
    0.41
     בעי
    0.41
    Activations Density 0.002%

    No Known Activations