© 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. 6939
    Prev
    Next
    INDEX
    Explanations

    it followed by negations

    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
    .}(
    -0.89
    時点で
    -0.85
     begle
    -0.77
    Nguy
    -0.76
    .].
    -0.74
    鏄
    -0.73
    oise
    -0.71
    🅣
    -0.70
     campuran
    -0.70
     飲み
    -0.70
    POSITIVE LOGITS
     not
    2.58
     weren
    2.56
     wasn
    2.42
     hadn
    1.70
     wasnt
    1.56
    不是
    1.48
    Wasn
    1.32
    wasn
    1.30
     Wasn
    1.28
     neby
    1.24
    Activations Density 0.013%

    No Known Activations