© 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. 173658
    Prev
    Next
    INDEX
    Explanations

    system errors or .dlls

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

    introductory labels

    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
    ཎ
    0.58
    ਨ
    0.56
     ਤੁ
    0.50
    製造
    0.48
    アシ
    0.48
    実験
    0.48
     निकालेंगे
    0.47
     ピ
    0.47
    벡터
    0.47
     વૃક્ષ
    0.47
    POSITIVE LOGITS
     management
    0.45
    0.42
     ((
    0.41
     faulted
    0.40
    SuppressWarnings
    0.40
     Ablauf
    0.39
    ((
    0.39
     dealt
    0.39
     condu
    0.39
     contested
    0.39
    Activations Density 0.000%

    No Known Activations