© 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. 113871
    Prev
    Next
    INDEX
    Explanations

    examples, tendencies, or explanations

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

    commonly used

    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
     filosofia
    0.51
    philosoph
    0.50
     Philosophie
    0.50
    感動
    0.50
     mantener
    0.48
    していますが
    0.47
    tekn
    0.46
    渺
    0.46
    energia
    0.46
     absolv
    0.45
    POSITIVE LOGITS
    比如说
    0.52
     example
    0.50
     unfairly
    0.49
    常见的
    0.47
    倾向
    0.47
     biasing
    0.47
    常见
    0.46
     например
    0.46
    )))
    0.46
    တဲ့
    0.46
    Activations Density 0.004%

    No Known Activations