© 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. 20026
    Prev
    Next
    INDEX
    Explanations

    cells perform processes

    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
    萂
    0.46
     WAR
    0.44
    苖
    0.43
     उसको
    0.41
     مو
    0.40
     Woman
    0.39
     Phần
    0.39
     রোনাল
    0.39
     공급
    0.39
    茷
    0.39
    POSITIVE LOGITS
    ade
    0.55
    iken
    0.47
    ende
    0.47
     cramping
    0.47
    সাধন
    0.46
    upaten
    0.46
    amination
    0.45
     diberikan
    0.45
    hane
    0.44
    addir
    0.44
    Activations Density 0.002%

    No Known Activations