© 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. 63929
    Prev
    Next
    INDEX
    Explanations

    people skills quality buildings

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

    emotional connection and intimacy

    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
    дентификаторы
    0.50
    疾病
    0.49
     захворю
    0.47
     UNNEEDED
    0.46
     SupCt
    0.46
    嵐
    0.46
    minIndex
    0.46
    IRQ
    0.45
    消毒
    0.45
    ონი
    0.44
    POSITIVE LOGITS
     Angel
    0.55
     Kate
    0.54
     Spotify
    0.52
     Holly
    0.51
     Fant
    0.50
     J
    0.50
    loa
    0.49
     Fantasy
    0.49
     Bridal
    0.49
     S
    0.49
    Activations Density 0.000%

    No Known Activations