© 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. 91870
    Prev
    Next
    INDEX
    Explanations

    operations, solution, monitors

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

    finding negative outcomes or exceptions

    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
     teased
    0.51
     purpose
    0.48
    ើន
    0.47
     teasing
    0.47
     জানুয়ার
    0.47
    tki
    0.47
    筍
    0.46
     propósito
    0.46
     হিন্দুদের
    0.46
    뮈
    0.45
    POSITIVE LOGITS
     as
    0.45
    сле
    0.43
    Ś
    0.41
     Speed
    0.40
    NE
    0.40
    مر
    0.40
     SSSR
    0.39
     Orrell
    0.39
    ска
    0.39
    पूर्व
    0.39
    Activations Density 0.000%

    No Known Activations