© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98054
    Prev
    Next
    INDEX
    Explanations

    code and structured text

    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
    modificar
    -0.75
    preparation
    -0.69
    Espero
    -0.69
    palabras
    -0.69
    centiles
    -0.68
     SAD
    -0.66
    フェクト
    -0.66
    Cecil
    -0.66
    detalle
    -0.65
    Rae
    -0.65
    POSITIVE LOGITS
     textil
    0.73
    gca
    0.69
    เข้า
    0.68
    xhtml
    0.68
     exige
    0.68
    gang
    0.67
     اليابان
    0.66
     garanti
    0.66
     censura
    0.66
     exchanging
    0.66
    Activations Density 0.089%

    No Known Activations