© 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. 10-GEMMASCOPE-RES-131K
    7. 87154
    Prev
    Next
    INDEX
    Explanations

    section heading

    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_10/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
     pernikahan
    -1.43
     lelaki
    -1.43
     ENGL
    -1.41
     WIDE
    -1.40
     Rods
    -1.39
    Cameroon
    -1.35
     HEAVEN
    -1.35
    ⦊
    -1.34
    razio
    -1.34
     krijgt
    -1.33
    POSITIVE LOGITS
    _
    1.77
    ↵↵
    1.57
    -
    1.48
     awesome
    1.34
     notorious
    1.33
    :
    1.32
     It
    1.30
    er
    1.29
     either
    1.27
     roughly
    1.26
    Activations Density 0.072%

    No Known Activations