© 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. 212983
    Prev
    Next
    INDEX
    Explanations

    spontaneous occurrence

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

    implied, tell, time, dataset, events

    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
    купно
    0.40
    ridges
    0.39
    バイル
    0.39
    stens
    0.38
     retreat
    0.38
     totalling
    0.38
    baiki
    0.37
    ｻ
    0.37
     servicing
    0.36
     retreating
    0.36
    POSITIVE LOGITS
     spont
    0.54
    异步
    0.52
     iemand
    0.50
     zaten
    0.49
     spontaneous
    0.49
     espont
    0.46
    某些
    0.46
     triggered
    0.46
     произо
    0.46
    自然
    0.45
    Activations Density 0.002%

    No Known Activations