© 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. 49502
    Prev
    Next
    INDEX
    Explanations

    preschool, Eusebius, phone, mini-bar, write

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

    generating multiple options

    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
    Е
    0.55
    Finally
    0.49
    医療
    0.49
    지막
    0.49
    zicht
    0.48
    Произ
    0.47
    Worst
    0.47
    сё
    0.47
    РУ
    0.46
    安
    0.46
    POSITIVE LOGITS
     missão
    0.49
     varient
    0.45
     cayenne
    0.44
    yata
    0.44
     composição
    0.44
     علا
    0.44
    ukan
    0.43
     beneficia
    0.42
     millón
    0.42
    DEPENDENCIA
    0.41
    Activations Density 0.000%

    No Known Activations