© 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. 135245
    Prev
    Next
    INDEX
    Explanations

    caresses, using, team, style, stop

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

    You can describe

    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
    ar
    0.50
    l
    0.48
    is
    0.48
    n
    0.47
    lar
    0.45
    an
    0.45
    ad
    0.44
     adsor
    0.43
    c
    0.43
    скі
    0.42
    POSITIVE LOGITS
     احنا
    0.52
    ペーン
    0.51
    时间内
    0.51
     而且
    0.50
    យើង
    0.50
     expressão
    0.49
     व्हा
    0.48
     我們
    0.48
     भेजा
    0.48
     ພວກເຮົາ
    0.48
    Activations Density 0.001%

    No Known Activations