© 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. 30961
    Prev
    Next
    INDEX
    Explanations

    following common words

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

    thinking of

    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
     Zav
    0.54
     შემთ
    0.48
     प्रयोग
    0.46
     Quỳnh
    0.46
    '>{
    0.44
     स्त्रीलिंग
    0.44
     Đoàn
    0.44
    multirow
    0.44
    remo
    0.44
    鿢
    0.43
    POSITIVE LOGITS
     completions
    0.46
     élèves
    0.45
     syllables
    0.45
    бро
    0.44
    intermediates
    0.43
    标识
    0.42
     മീ
    0.42
     moduleId
    0.42
     placeholders
    0.42
     tackling
    0.41
    Activations Density 0.000%

    No Known Activations