© 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. 43701
    Prev
    Next
    INDEX
    Explanations

    years since

    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
     cikk
    -1.59
    だけではなく
    -1.58
     disques
    -1.52
     étan
    -1.51
     célè
    -1.49
     wonderful
    -1.49
     interessante
    -1.48
     mété
    -1.45
    ญี่ป
    -1.45
    罟
    -1.45
    POSITIVE LOGITS
     because
    1.70
     These
    1.54
     four
    1.50
     two
    1.48
     to
    1.48
     one
    1.47
     three
    1.47
     on
    1.45
     when
    1.39
    !!!!!
    1.34
    Activations Density 0.022%

    No Known Activations