© 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. 225425
    Prev
    Next
    INDEX
    Explanations

    define, guided, or charged

    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
     dữ
    0.52
    Ữ
    0.50
     данными
    0.49
     유사
    0.49
     Ayl
    0.49
     상세
    0.47
     مِنْ
    0.46
     哈
    0.46
     ಪ್ರಾರಂಭ
    0.45
     với
    0.45
    POSITIVE LOGITS
     onda
    0.46
    必
    0.46
    fta
    0.45
    ിക്കു
    0.44
    Resize
    0.42
     बचें
    0.42
    Define
    0.42
    guided
    0.42
     integrado
    0.42
     naudoj
    0.42
    Activations Density 0.000%

    No Known Activations