© 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. 12126
    Prev
    Next
    INDEX
    Explanations

    the [category]

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

    data and dataset

    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
     ਅਤੇ
    0.50
     and
    0.49
     thiab
    0.47
    8
    0.47
     are
    0.46
    及び
    0.46
     và
    0.45
    และ
    0.45
    ＆
    0.44
     és
    0.43
    POSITIVE LOGITS
     iemand
    0.41
    accouchement
    0.40
     문제가
    0.38
    这个人
    0.38
    ставить
    0.37
     그것
    0.37
     квартиру
    0.37
    aparikkh
    0.36
     вопроса
    0.36
    鼾
    0.36
    Activations Density 0.000%

    No Known Activations