© 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. 101451
    Prev
    Next
    INDEX
    Explanations

    listing category items

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

    Prometheus, legend, head

    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
    뮤
    0.50
     새로운
    0.50
    िकी
    0.48
     뮤
    0.46
     ಹೊಸ
    0.45
     божомолу
    0.45
     intellectually
    0.45
     역사
    0.44
    weaving
    0.44
    зит
    0.43
    POSITIVE LOGITS
    ....
    0.57
    。
    0.57
    ।
    0.55
     to
    0.54
    fiere
    0.50
     en
    0.49
    ，
    0.49
    FE
    0.48
    W
    0.48
    H
    0.47
    Activations Density 0.001%

    No Known Activations