© 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. 2546
    Prev
    Next
    INDEX
    Explanations

    zynga poker

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

    chess board represented

    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
     reintroduced
    0.54
    man
    0.52
     revamped
    0.51
    tr
    0.51
     intrinsically
    0.49
    mi
    0.48
    k
    0.48
    li
    0.48
    ીએ
    0.47
     technologically
    0.47
    POSITIVE LOGITS
     amelyek
    0.54
     agua
    0.53
     ferrug
    0.50
     पढ़ाई
    0.49
     Biał
    0.49
     إذا
    0.49
    ؟.
    0.48
     था
    0.47
     -.
    0.47
    ?..
    0.46
    Activations Density 0.000%

    No Known Activations