© 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. 161189
    Prev
    Next
    INDEX
    Explanations

    times and specific dates

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

    grammatical irregularities

    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
     electrónica
    0.55
     учи
    0.49
     телефо
    0.48
     координаты
    0.47
     सिले
    0.46
     avion
    0.46
    噗
    0.46
    ӓ
    0.46
    еди
    0.46
    sled
    0.46
    POSITIVE LOGITS
    Strategy
    0.48
    :",
    0.45
    Months
    0.45
    :
    0.44
    ন্‌
    0.43
     kısm
    0.43
    Callback
    0.42
    当時の
    0.42
    Classic
    0.42
    λλά
    0.42
    Activations Density 0.000%

    No Known Activations