© 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. 203825
    Prev
    Next
    INDEX
    Explanations

    awards and achievements

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

    after a

    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
     oude
    0.43
    eleg
    0.43
    hér
    0.43
    id
    0.43
    as
    0.42
    depends
    0.42
    🍮
    0.42
    i
    0.41
    iende
    0.40
    혁
    0.40
    POSITIVE LOGITS
     Gainesville
    0.56
    ният
    0.53
     هز
    0.49
    razier
    0.49
     夏季
    0.48
     Annapolis
    0.48
    밌
    0.47
     Дні
    0.47
     зем
    0.47
     ካ
    0.46
    Activations Density 0.001%

    No Known Activations