© 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. 7897
    Prev
    Next
    INDEX
    Explanations

    leisurely activities and relaxation

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

    home entertaining and leisure

    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
    😡
    0.55
     मुसलमान
    0.52
     prostit
    0.50
    😠
    0.47
     prostitutes
    0.46
    😭😭
    0.46
    uberculosis
    0.45
     readable
    0.44
     ด่า
    0.44
    👎
    0.43
    POSITIVE LOGITS
     অতিথ
    0.68
     lounging
    0.65
     evenings
    0.64
     mornings
    0.63
     guests
    0.63
     leisurely
    0.59
     menikmati
    0.57
     veya
    0.56
     huéspedes
    0.56
     invitados
    0.56
    Activations Density 0.305%

    No Known Activations