© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 19829
    Prev
    Next
    INDEX
    Explanations

    currency, calculation, time, investment

    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
    actif
    0.50
     سنو
    0.50
    igd
    0.46
    iddy
    0.45
    addena
    0.42
    螈
    0.42
    ontan
    0.42
    lington
    0.41
    iewicz
    0.41
    roductive
    0.41
    POSITIVE LOGITS
     денег
    0.42
     corresponding
    0.41
     seizures
    0.41
     &
    0.40
     $
    0.40
     金
    0.39
     потрі
    0.39
     limelight
    0.39
     inégal
    0.38
     name
    0.38
    Activations Density 0.001%

    No Known Activations