© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 30697
    Prev
    Next
    INDEX
    Explanations

    non-english scripts

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

    but existing laws

    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
     (
    0.45
    )]
    0.45
     Gale
    0.41
     PDF
    0.40
     ofthe
    0.38
    ,
    0.38
     Aldrich
    0.38
     theories
    0.37
     Theories
    0.37
    POSITIVE LOGITS
    dn
    0.59
    पिक्सल
    0.55
     билан
    0.52
    फेक्ट
    0.51
    ទំនាក់
    0.50
     દિવસ
    0.49
    𝖽
    0.48
    म्पियन
    0.48
     செயல்ப
    0.48
     ഓഫീ
    0.48
    Activations Density 0.000%

    No Known Activations