© 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. 151212
    Prev
    Next
    INDEX
    Explanations

    for any; cannot verify

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

    Girls struggle with pressure

    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
    tra
    0.57
    a
    0.54
    ates
    0.53
    policies
    0.52
    ira
    0.51
    sent
    0.51
    lest
    0.51
    blocks
    0.50
    tuk
    0.50
    eb
    0.50
    POSITIVE LOGITS
     Cindy
    0.49
     consideración
    0.47
     nữ
    0.46
    ใน
    0.45
     PLN
    0.45
     в
    0.44
     gegen
    0.44
     perhatian
    0.43
     Angular
    0.43
    निश्ड
    0.43
    Activations Density 0.000%

    No Known Activations