© 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. 204727
    Prev
    Next
    INDEX
    Explanations

    came from

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

    for the

    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
    EnglishMarks
    0.54
    电子商务
    0.53
    镟
    0.52
    殚
    0.52
    缜
    0.51
    MathMarks
    0.50
     కుటు
    0.49
    बच्चों
    0.48
     மற்றொரு
    0.48
    毉
    0.48
    POSITIVE LOGITS
     garlic
    0.48
     T
    0.45
     C
    0.45
    ....
    0.44
     ingot
    0.44
    ….
    0.43
     ACT
    0.42
     Actin
    0.42
    hline
    0.42
     gota
    0.42
    Activations Density 0.001%

    No Known Activations