© 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. 122082
    Prev
    Next
    INDEX
    Explanations

    ecommerce companies, clothes websites, director

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

    yourself

    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
    bam
    0.52
    encore
    0.50
    imm
    0.50
    iml
    0.48
    elit
    0.48
    neo
    0.47
     o
    0.47
     b
    0.46
    umo
    0.46
    unpkg
    0.46
    POSITIVE LOGITS
    しば
    0.45
     ").
    0.43
     لاءِ
    0.42
    ).*
    0.42
    UserManager
    0.42
     Usuarios
    0.42
    شتی
    0.41
     Información
    0.40
    設計
    0.40
     señales
    0.39
    Activations Density 0.001%

    No Known Activations