© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 40813
    Prev
    Next
    INDEX
    Explanations

    naturally occurring

    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
     administrativo
    0.50
     ребенок
    0.49
    胭
    0.48
     администра
    0.45
     transportar
    0.44
     ребенка
    0.44
     transporter
    0.44
     ребён
    0.43
     सैफ
    0.43
     vouchers
    0.43
    POSITIVE LOGITS
    a
    0.64
    er
    0.59
    ق
    0.59
    o
    0.58
    ai
    0.57
    bo
    0.57
    AG
    0.55
    SERT
    0.55
    ov
    0.54
    ER
    0.53
    Activations Density 0.011%

    No Known Activations