© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112906
    Prev
    Next
    INDEX
    Explanations

    date, month, projection, ports

    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
    !
    -1.59
    __":
    -1.55
    <strong>
    -1.52
    u
    -1.41
    石垣
    -1.41
    ।
    -1.38
    q
    -1.30
    Begin
    -1.28
     них
    -1.27
    .”
    -1.26
    POSITIVE LOGITS
    courir
    1.33
     daarvan
    1.33
     cinquième
    1.32
     tzu
    1.30
    グルト
    1.26
    䥑
    1.25
    Appellants
    1.23
    Curtir
    1.23
    visuel
    1.23
    と言える
    1.22
    Activations Density 0.003%

    No Known Activations