© 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. 53898
    Prev
    Next
    INDEX
    Explanations

    sleeping and being asleep

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

    sleeping and slumber

    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
    ney
    0.62
    ból
    0.58
    ación
    0.57
    nement
    0.56
    '
    0.54
    c
    0.54
    cing
    0.53
    ется
    0.52
     distressing
    0.52
    r
    0.51
    POSITIVE LOGITS
    TON
    0.55
     Sleeping
    0.54
     ส
    0.54
     Gemeinde
    0.54
     sinnv
    0.50
     Partei
    0.50
     vykon
    0.49
     Sword
    0.48
     Partai
    0.48
    的日子
    0.48
    Activations Density 0.047%

    No Known Activations