© 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. 102512
    Prev
    Next
    INDEX
    Explanations

    California, industry, week

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

    recognise or foreign/technical terms

    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
     Казино
    0.52
    n
    0.52
    中
    0.51
     Stad
    0.50
    碧
    0.49
    藩
    0.49
     然而
    0.47
    的主
    0.47
     比
    0.47
    旌
    0.46
    POSITIVE LOGITS
    othing
    0.55
     recognise
    0.55
    اء
    0.50
     призна
    0.49
     इनमें
    0.46
    ittle
    0.45
     ß
    0.45
     recognises
    0.45
    ospace
    0.44
     relentlessly
    0.44
    Activations Density 0.000%

    No Known Activations