© 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. 222908
    Prev
    Next
    INDEX
    Explanations

    year-old followed by a descriptor

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

    code examples and programming concepts

    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
    t
    0.48
    e
    0.47
     myelin
    0.46
     arcs
    0.45
    ا
    0.44
    \
    0.44
     colors
    0.43
    m
    0.43
    xx
    0.41
     $(\
    0.41
    POSITIVE LOGITS
    ૌ
    0.54
     SELF
    0.53
    ENSATION
    0.52
     ايضا
    0.50
     також
    0.50
     artistas
    0.48
    汽車
    0.48
     PARTIC
    0.48
    Ola
    0.47
    વણી
    0.46
    Activations Density 0.001%

    No Known Activations