© 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. 86942
    Prev
    Next
    INDEX
    Explanations

    pupils and learners

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

    where it gets interesting

    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
    ˁ
    0.47
    йы
    0.42
     পুনরায়
    0.41
    ;
    0.40
    已经被
    0.40
    had
    0.40
    keen
    0.40
     series
    0.39
    are
    0.39
    ),
    0.39
    POSITIVE LOGITS
     ambul
    0.52
     chercheurs
    0.52
     Kontext
    0.50
     Ambul
    0.47
    𒅁
    0.47
     مدرسه
    0.46
     interdiscipl
    0.45
     diffère
    0.45
     arterioles
    0.45
     heterogeneity
    0.45
    Activations Density 0.000%

    No Known Activations