© 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. 36070
    Prev
    Next
    INDEX
    Explanations

    expressing feelings or opinions

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

    expressing thoughts, feelings, or opinions

    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
    swering
    0.66
    providing
    0.64
    celain
    0.62
    ки
    0.61
     einfacher
    0.60
    nies
    0.59
    ఎ
    0.59
     postérieurs
    0.58
    ವರೆ
    0.56
    䙲
    0.56
    POSITIVE LOGITS
    s
    0.99
    ς
    0.82
     wyra
    0.73
     express
    0.71
    表达
    0.71
     выра
    0.69
     expresses
    0.66
     expres
    0.64
     표현
    0.63
     expresó
    0.63
    Activations Density 0.032%

    No Known Activations