© 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. 32585
    Prev
    Next
    INDEX
    Explanations

    synthetic voice or monitor

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

    open source

    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
    أ
    0.50
    아
    0.48
     мяс
    0.48
    او
    0.47
    設立
    0.47
     escuelas
    0.46
    нцип
    0.46
    йд
    0.46
    QUA
    0.45
    йда
    0.45
    POSITIVE LOGITS
     surcharge
    0.56
     favorite
    0.50
    ᷄
    0.48
     Dyson
    0.48
     Favorite
    0.45
     Sui
    0.44
     disperse
    0.44
     Choir
    0.44
    colare
    0.44
     Meter
    0.43
    Activations Density 0.000%

    No Known Activations