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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32336
    Prev
    Next
    INDEX
    Explanations

    in writing

    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
    ticularly
    -0.73
    ouwd
    -0.73
     období
    -0.67
    ฌ
    -0.66
     assunto
    -0.66
    uoš
    -0.66
     Paine
    -0.66
    ներ
    -0.66
    ects
    -0.65
     Mage
    -0.65
    POSITIVE LOGITS
     writing
    6.47
    writing
    4.78
     Writing
    4.63
    Writing
    4.59
     WRITING
    3.83
     writings
    3.28
    WRITING
    3.27
     write
    2.73
     wrote
    2.66
     written
    2.64
    Activations Density 0.052%

    No Known Activations