© 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. 102451
    Prev
    Next
    INDEX
    Explanations

    URLs, web paths, and identifiers

    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
     rodillas
    -0.71
    총
    -0.70
     gruppi
    -0.69
    iliger
    -0.69
     groups
    -0.68
    projectName
    -0.67
     knots
    -0.67
     Unterscheidung
    -0.66
     총
    -0.66
    usalem
    -0.65
    POSITIVE LOGITS
     जु
    0.78
     Olin
    0.76
    VISIBLE
    0.72
     pecuniary
    0.72
    widetilde
    0.71
    ဦ
    0.70
     Loren
    0.70
     heures
    0.70
    หนึ่ง
    0.70
    FLEX
    0.69
    Activations Density 0.032%

    No Known Activations