© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110498
    Prev
    Next
    INDEX
    Explanations

    programming contexts and prepositional phrases

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

    the word "on" in technical or formal contexts, particularly in code, compound terms, and prepositions indicating dates or dependencies.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    -3.03
    a
    -3.02
    ſſel
    -3.02
     on
    -2.83
     offers
    -2.80
     was
    -2.78
     have
    -2.77
     takes
    -2.73
    as
    -2.72
     tells
    -2.72
    POSITIVE LOGITS
    ↵↵
    3.30
    厹
    3.16
    瞜
    2.94
    Ꮉ
    2.63
    釕
    2.56
     glistening
    2.55
    蟜
    2.53
    囖
    2.52
     dejected
    2.52
     blaue
    2.52
    Activations Density 0.010%

    No Known Activations