© 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. 175272
    Prev
    Next
    INDEX
    Explanations

    clandestinité

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

    next step, October and

    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
    Total
    0.44
    最终
    0.43
    Schn
    0.42
    T
    0.42
    ियां
    0.41
    总
    0.41
    øy
    0.41
    工厂
    0.41
    ellini
    0.40
    TotalPrice
    0.40
    POSITIVE LOGITS
     clandest
    0.51
     destes
    0.50
    鿢
    0.45
     habis
    0.45
     devemos
    0.45
     bersama
    0.44
     chez
    0.44
     coloque
    0.43
     despacho
    0.43
     permettra
    0.43
    Activations Density 0.001%

    No Known Activations