© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    American Physical Society

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

    words followed by specific punctuation

    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
     quelquefois
    0.39
    பாளையம்
    0.39
    ofd
    0.38
    ซึ่ง
    0.38
     সাধারণভাবে
    0.38
    org
    0.38
    ouflage
    0.38
    爻
    0.38
    一般的
    0.38
    你在
    0.38
    POSITIVE LOGITS
     commitment
    0.52
     Nen
    0.45
     Ard
    0.45
     membership
    0.44
     leadership
    0.43
     karar
    0.43
     legislative
    0.42
     CHOICE
    0.42
     his
    0.41
     symbolically
    0.41
    Activations Density 0.000%

    No Known Activations