© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85865
    Prev
    Next
    INDEX
    Explanations

    ars, collection. trade, help, fine

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

    alien human behaviour studying

    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
    Negative Logits
    SUCCESS
    0.50
    METHODS
    0.49
    пі
    0.48
    NRC
    0.48
    ﺍ
    0.47
    Zawodnik
    0.46
    ૨
    0.46
     ಆರಂಭ
    0.45
    ೯
    0.45
    RIC
    0.44
    POSITIVE LOGITS
     stupid
    0.44
     deteriorated
    0.44
     potty
    0.43
     Beaut
    0.42
     housework
    0.42
     poetic
    0.41
     deteriorating
    0.41
     donde
    0.41
     deterior
    0.41
     disintegr
    0.41
    Activations Density 0.006%

    No Known Activations