© 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. 83721
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    Ond
    -0.78
     left
    -0.72
    协
    -0.72
    srv
    -0.69
    InkWell
    -0.69
     srv
    -0.67
     mahu
    -0.66
     degust
    -0.66
    ִ
    -0.66
    dimen
    -0.64
    POSITIVE LOGITS
     microscopy
    0.75
    ácii
    0.71
     Choice
    0.71
    タマ
    0.70
    valdi
    0.69
    assi
    0.68
     Couch
    0.67
    ignoire
    0.67
    _);
    0.65
    žiu
    0.65
    Activations Density 0.052%

    No Known Activations