© 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. 50492
    Prev
    Next
    INDEX
    Explanations

    walk through

    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
     to
    -1.06
    หว่าง
    -0.79
    iação
    -0.78
     去
    -0.77
     yetu
    -0.76
    感想
    -0.75
    ٕ
    -0.73
    ;">
    -0.73
     vif
    -0.70
    (ﾟ
    -0.70
    POSITIVE LOGITS
     step
    1.65
     through
    1.59
    step
    1.44
    walk
    1.33
    Step
    1.33
     walk
    1.31
     walkthrough
    1.27
     walks
    1.22
     Step
    1.17
    Walk
    1.12
    Activations Density 0.011%

    No Known Activations