© 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. 68552
    Prev
    Next
    INDEX
    Explanations

    Wile E. Coyote's ACME spectacles

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

    professional friend

    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
     I
    0.56
     Q
    0.49
     Thread
    0.49
     ";
    0.46
    int
    0.45
     \|\
    0.45
     A
    0.44
     Word
    0.43
     "(
    0.43
     ","
    0.43
    POSITIVE LOGITS
     पाण्डे
    0.54
    وس
    0.49
    旎
    0.48
    呂
    0.47
     realizzazione
    0.47
    제의
    0.46
    പ്പാ
    0.46
    퐶
    0.46
     Cina
    0.45
    ोल
    0.45
    Activations Density 0.001%

    No Known Activations