© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 28367
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency or limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    1.13
     for
    0.76
    re
    0.71
    od
    0.70
     man
    0.69
    ai
    0.67
    ні
    0.67
    ו
    0.66
    ำ
    0.66
     glimps
    0.66
    POSITIVE LOGITS
     Antennes
    0.88
    legten
    0.87
    irrahim
    0.80
     Sociales
    0.80
    qk
    0.80
    kyverno
    0.80
    probs
    0.79
    _*
    0.77
    Dg
    0.77
    讐
    0.75
    Activations Density 0.279%

    No Known Activations