© 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. 31874
    Prev
    Next
    INDEX
    Explanations

    word endings like ography, ishing, bing, ism

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

    theory and concepts

    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
     如何
    0.44
    Rou
    0.42
    ceti
    0.40
    要想
    0.40
    炲
    0.40
    importanza
    0.40
     মজুমদার
    0.39
    quando
    0.39
     لگاتا
    0.38
    oniazid
    0.38
    POSITIVE LOGITS
    |
    0.55
     Silicone
    0.46
     of
    0.46
     SRAM
    0.45
     not
    0.45
     HBO
    0.45
     HVAC
    0.45
    ของ
    0.44
     ohne
    0.43
     nicht
    0.43
    Activations Density 0.012%

    No Known Activations