© 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. 236047
    Prev
    Next
    INDEX
    Explanations

    lottery, year, segment, used, numbers

    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
    ौला
    0.44
    enge
    0.42
     sanctions
    0.41
    nitz
    0.41
    铁
    0.40
    าตุ
    0.40
    afar
    0.40
    อำ
    0.39
     freezes
    0.39
    एचओ
    0.39
    POSITIVE LOGITS
     tengo
    0.56
     پاب
    0.56
    `:
    0.55
     czy
    0.52
     Lottery
    0.51
     cambiare
    0.51
     Considerando
    0.51
     Vamos
    0.50
     lottery
    0.50
     და
    0.50
    Activations Density 0.000%

    No Known Activations