© 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. 19423
    Prev
    Next
    INDEX
    Explanations

    exception passing

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

    error messages and code blocks

    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
     odpad
    0.46
     निराश
    0.44
    ❎
    0.43
    れて
    0.43
    👎
    0.42
     rejects
    0.42
    reject
    0.42
     Пла
    0.41
    ❌
    0.41
    orno
    0.41
    POSITIVE LOGITS
    طور
    0.45
    FTP
    0.42
    Flatten
    0.42
    GOLD
    0.39
    caused
    0.39
    FAT
    0.39
    Caught
    0.39
    illera
    0.39
     CAE
    0.38
     cause
    0.38
    Activations Density 0.002%

    No Known Activations