© 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. 65837
    Prev
    Next
    INDEX
    Explanations

    html id attributes

    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
     sò
    -1.42
     pronounced
    -1.41
     on
    -1.37
     possible
    -1.36
    This
    -1.34
     through
    -1.34
     being
    -1.33
     
    -1.32
     up
    -1.30
     noticeable
    -1.30
    POSITIVE LOGITS
     nya
    1.63
     proposé
    1.58
    熜
    1.57
     proposée
    1.55
     midst
    1.55
     simpel
    1.54
    ߠ
    1.51
     نوز
    1.49
    崀
    1.48
     człowiek
    1.48
    Activations Density 0.015%

    No Known Activations