© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46603
    Prev
    Next
    INDEX
    Explanations

    occupation followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onesian
    0.40
    مس
    0.39
    rules
    0.38
    วันที่
    0.37
    ስተ
    0.36
    ර
    0.36
     About
    0.36
     Rules
    0.36
     Cultura
    0.36
    localized
    0.36
    POSITIVE LOGITS
    YES
    0.42
    utivo
    0.41
    Tabla
    0.41
     pistas
    0.40
    лятор
    0.39
     cero
    0.38
     povo
    0.38
    тпу
    0.38
    яна
    0.38
    <unused976>
    0.37
    Activations Density 0.012%

    No Known Activations