© 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. 60442
    Prev
    Next
    INDEX
    Explanations

    programming and code constructs

    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
    acrylamide
    -0.76
    tpl
    -0.76
     Tribal
    -0.73
     tawny
    -0.72
     Year
    -0.71
    mistic
    -0.70
    대로
    -0.70
     предме
    -0.70
    issional
    -0.69
     Reihe
    -0.68
    POSITIVE LOGITS
    utilisons
    0.81
    ||||||||
    0.81
    ===========
    0.80
    liggende
    0.79
    SCOPE
    0.76
    tiden
    0.75
    agod
    0.74
    pue
    0.74
     perfecta
    0.74
    zym
    0.74
    Activations Density 0.021%

    No Known Activations