© 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. 128248
    Prev
    Next
    INDEX
    Explanations

    special characters and foreign words

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

    textual descriptions and structures

    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
     neoclassical
    0.52
    スマス
    0.51
     workstation
    0.51
    alee
    0.51
    흄
    0.48
    フレーム
    0.47
     fullback
    0.47
     fray
    0.47
     flue
    0.47
     Cosmology
    0.46
    POSITIVE LOGITS
    Př
    0.46
    ०
    0.44
     gerçekleşt
    0.43
    Ö
    0.43
    ด
    0.42
    Е
    0.42
    Ᏸ
    0.42
    epers
    0.41
    ە
    0.41
    %\
    0.40
    Activations Density 0.001%

    No Known Activations