© 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. 170053
    Prev
    Next
    INDEX
    Explanations

    automatic operations

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

    sensor cooking, individual merit

    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
     endorse
    0.56
     illustrate
    0.55
     ਚ
    0.55
    ders
    0.53
     endorsements
    0.51
     coworkers
    0.50
     presum
    0.50
    が通販
    0.50
     authorize
    0.50
     superbe
    0.50
    POSITIVE LOGITS
    umb
    0.49
     Gust
    0.49
     عض
    0.46
    寻
    0.44
    可持续
    0.44
    cyclic
    0.42
     Kal
    0.41
    یز
    0.40
     Tribal
    0.40
     pribli
    0.40
    Activations Density 0.000%

    No Known Activations