© 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. 145040
    Prev
    Next
    INDEX
    Explanations

    foreign words and technical terms

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

    for `num_` or `proportion`

    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
    position
    0.61
    postion
    0.49
     position
    0.47
     ,
    0.47
    top
    0.47
     -
    0.47
     $+$
    0.46
     +
    0.46
    ation
    0.46
    to
    0.46
    POSITIVE LOGITS
     tropomyosin
    0.52
     სამ
    0.48
     aurez
    0.48
     النف
    0.46
     مرحبا
    0.46
     amperes
    0.45
    ément
    0.45
     smelled
    0.44
     نجي
    0.43
     طويلة
    0.43
    Activations Density 0.000%

    No Known Activations