© 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. 49433
    Prev
    Next
    INDEX
    Explanations

    former public, statistics:, feel free, tap into

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

    just saying

    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
    \
    0.47
    只需要
    0.43
    няется
    0.42
    ंबे
    0.41
    ʳ
    0.41
     reimag
    0.41
    ᾰ
    0.41
    genommen
    0.40
    真的是
    0.40
     není
    0.40
    POSITIVE LOGITS
     सबूत
    0.46
    鳩
    0.46
     surpluses
    0.43
     Kinh
    0.42
     発
    0.41
     چاہتے
    0.41
     grantees
    0.41
     သူ
    0.40
    ogran
    0.40
     dislike
    0.40
    Activations Density 0.000%

    No Known Activations