© 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. 34-GEMMASCOPE-RES-131K
    7. 102777
    Prev
    Next
    INDEX
    Explanations

    programming language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ТР
    -0.78
    CHAR
    -0.76
    cadena
    -0.72
     guiding
    -0.72
     á
    -0.71
    Ğ
    -0.71
     assessing
    -0.70
    ajemen
    -0.69
     Estar
    -0.69
     Morel
    -0.68
    POSITIVE LOGITS
    Popularity
    0.83
    acked
    0.79
     vigour
    0.77
    Fiz
    0.75
     Integer
    0.75
    皑
    0.75
     πρω
    0.74
    なかったので
    0.73
    Kk
    0.73
    Anexo
    0.73
    Activations Density 0.003%

    No Known Activations