© 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. 91305
    Prev
    Next
    INDEX
    Explanations

    string formatting and methods

    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
     remaining
    -0.79
    など
    -0.76
    pherson
    -0.76
    ماند
    -0.75
    ração
    -0.75
    蛉
    -0.72
     Remaining
    -0.72
     buku
    -0.72
     país
    -0.71
     aerolí
    -0.71
    POSITIVE LOGITS
    valueOf
    1.37
     valueOf
    1.13
     stools
    0.79
     spørsmål
    0.79
     Сле
    0.77
     reformat
    0.77
    format
    0.77
     कु
    0.76
    vateľov
    0.76
    бочки
    0.75
    Activations Density 0.002%

    No Known Activations