© 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. 174208
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases

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

    specific parts or with additives

    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
    りと
    0.46
     sát
    0.42
    gesch
    0.41
     ence
    0.41
    щика
    0.40
    sleeping
    0.40
    िमा
    0.39
    奋
    0.39
    ان
    0.39
    chluss
    0.38
    POSITIVE LOGITS
     Wro
    0.50
     ਟ
    0.49
    樺
    0.48
    譙
    0.47
     Congo
    0.47
     strikers
    0.46
     চাপের
    0.46
    রাজের
    0.46
     Иванов
    0.46
     striker
    0.46
    Activations Density 0.000%

    No Known Activations