© 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. 44330
    Prev
    Next
    INDEX
    Explanations

    secure code, one of, come to

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

    help with problems

    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
    (\
    0.46
    _{(
    0.46
    pearl
    0.43
     tân
    0.43
    និត
    0.42
    op
    0.41
    -\
    0.41
     maga
    0.41
     pearls
    0.41
    ሆነ
    0.40
    POSITIVE LOGITS
     fermé
    0.51
    ılan
    0.49
    ı
    0.49
     هزار
    0.48
     গায়ে
    0.48
     یعنی
    0.47
    二维码
    0.46
    patched
    0.46
    нням
    0.46
     ज़रूर
    0.45
    Activations Density 0.000%

    No Known Activations