© 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. 7069
    Prev
    Next
    INDEX
    Explanations

    under a noun

    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
    כונות
    -1.58
     that
    -1.51
     unglaub
    -1.41
    hoge
    -1.38
    姩
    -1.34
    锘
    -1.34
    
    -1.33
    intendo
    -1.32
     rebajas
    -1.32
    ایق
    -1.30
    POSITIVE LOGITS
     of
    2.27
    “
    1.55
    www
    1.52
    ll
    1.40
     .
    1.39
    U
    1.39
    ou
    1.37
    <i>
    1.36
    za
    1.31
    Link
    1.31
    Activations Density 0.052%

    No Known Activations