© 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. 60021
    Prev
    Next
    INDEX
    Explanations

    letters to the editor

    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
    assigns
    -0.75
    kete
    -0.72
     (±
    -0.71
    ások
    -0.70
     日
    -0.69
     nhôm
    -0.68
    Diction
    -0.68
     projeto
    -0.67
    ayang
    -0.66
     ต
    -0.66
    POSITIVE LOGITS
     editor
    2.52
     editors
    2.31
    Editor
    2.28
    editor
    2.20
     Editor
    2.19
     Editors
    1.92
    EDITOR
    1.88
     EDITOR
    1.84
    editors
    1.77
     editorial
    1.76
    Activations Density 0.002%

    No Known Activations