© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205991
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    number of legs

    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
     Error
    0.50
    Чтобы
    0.46
    為了
    0.46
     வரும்
    0.46
    为了
    0.41
     Sampling
    0.41
    kens
    0.40
    </h2>
    0.40
    errors
    0.40
     Gm
    0.40
    POSITIVE LOGITS
    ">⁡</
    0.46
     হাইড্রোজেন
    0.45
     spokesman
    0.42
    ঞ্
    0.41
    డియో
    0.41
    ーフ
    0.41
    ದ್ರ
    0.41
     সময়ে
    0.39
    ડિયો
    0.39
    駆
    0.39
    Activations Density 0.001%

    No Known Activations