© 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. 117974
    Prev
    Next
    INDEX
    Explanations

    percentages and non-English characters

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

    free, pay, fracturing

    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
    Negative Logits
    lier
    0.48
     nourishing
    0.40
    ᖕ
    0.40
     kullanarak
    0.40
     hydrating
    0.39
     monoton
    0.38
     lifting
    0.37
     неуда
    0.37
     Manu
    0.37
     spost
    0.37
    POSITIVE LOGITS
    plats
    0.50
    การ
    0.50
    ซ
    0.49
    。。
    0.47
     字
    0.47
    मध्ये
    0.46
    あの
    0.46
    彩
    0.46
    СП
    0.45
    CUIT
    0.45
    Activations Density 0.005%

    No Known Activations