© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70196
    Prev
    Next
    INDEX
    Explanations

    describing initial state or condition

    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
    却不
    -1.64
     einiges
    -1.63
     verschiedene
    -1.63
    却没有
    -1.60
     twarzy
    -1.58
    が多
    -1.55
    <
    -1.51
    /}{
    -1.49
    kozások
    -1.47
    ということを
    -1.47
    POSITIVE LOGITS
     Additionally
    1.71
    ſelves
    1.64
     nebo
    1.63
     secos
    1.62
     With
    1.52
     造型
    1.48
     Essentially
    1.48
     otro
    1.48
     any
    1.47
     it
    1.46
    Activations Density 0.042%

    No Known Activations