© 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. 200210
    Prev
    Next
    INDEX
    Explanations

    brightening, scary, expected, average

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

    foreign words and scripts

    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
     preventative
    0.55
     scler
    0.48
     "
    0.46
     permissible
    0.46
    ет
    0.44
    ற்கான
    0.43
     turnkey
    0.43
     disabling
    0.43
     rented
    0.42
     people
    0.42
    POSITIVE LOGITS
     環
    0.52
     गाइस
    0.50
    شاہ
    0.49
     орби
    0.49
     حلقه
    0.48
     खूब
    0.47
    芏
    0.46
    夢
    0.45
     Обе
    0.44
     போலவே
    0.44
    Activations Density 0.001%

    No Known Activations