© 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. 107919
    Prev
    Next
    INDEX
    Explanations

    reference to expectations

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

    which species or not to

    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
    おり
    0.47
    Ἀ
    0.46
     pushed
    0.45
     alarmed
    0.43
    спубли
    0.43
     pigments
    0.43
    柔
    0.43
     интеллек
    0.43
     validInput
    0.43
     Argy
    0.42
    POSITIVE LOGITS
     MODIFY
    0.52
    thor
    0.51
    an
    0.50
    apr
    0.46
     ਜਾਣ
    0.45
     這
    0.45
    Brazilian
    0.44
    يئة
    0.43
     व्ही
    0.43
     ค่ะ
    0.43
    Activations Density 0.000%

    No Known Activations