© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219383
    Prev
    Next
    INDEX
    Explanations

    verbs followed by participles

    np_acts-logits-general · gemini-2.5-flash-lite

    beyond what's already known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mie
    0.50
    ެވެ
    0.49
    ם
    0.47
    ค่า
    0.47
    ޙ
    0.47
    ərd
    0.46
    .**
    0.46
    cmml
    0.45
    ColorLegend
    0.45
     eloku
    0.45
    POSITIVE LOGITS
    ignored
    0.53
     dread
    0.43
     mitochondrial
    0.43
     labelled
    0.43
     compatible
    0.43
    льное
    0.43
    屁
    0.42
     rumoured
    0.42
    ऱ
    0.42
     yield
    0.42
    Activations Density 0.000%

    No Known Activations