© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8417
    Prev
    Next
    INDEX
    Explanations

    movement out

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

    out of

    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_53_width_65k_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
    outs
    0.71
     outs
    0.64
    外
    0.51
    outer
    0.48
    от
    0.47
    在外
    0.46
     Outs
    0.46
    出去
    0.46
     outward
    0.45
    외
    0.45
    POSITIVE LOGITS
     outta
    1.85
    OutOf
    1.57
    outof
    1.44
     khỏi
    0.95
    ออกจาก
    0.94
     із
    0.93
     из
    0.91
     daraus
    0.85
    ből
    0.80
    ból
    0.78
    Activations Density 0.083%

    No Known Activations