© 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. 84457
    Prev
    Next
    INDEX
    Explanations

    code licenses and copyright

    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
    Vä
    -0.82
    ╫
    -0.78
    öner
    -0.72
    ἐ
    -0.72
    Wine
    -0.72
    Xoa
    -0.71
    componentWill
    -0.71
     toe
    -0.71
     chromatin
    -0.71
    Symfony
    -0.70
    POSITIVE LOGITS
     Howard
    0.74
     Fourteen
    0.73
    fif
    0.73
     Thirteen
    0.69
     Fifteen
    0.69
     Thirteenth
    0.68
     YA
    0.68
     phải
    0.66
     Huh
    0.66
     Ahmed
    0.65
    Activations Density 0.594%

    No Known Activations