© 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. 99984
    Prev
    Next
    INDEX
    Explanations

    mathematical variable n

    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
     not
    -1.42
    trägen
    -1.30
     也
    -1.30
    几个
    -1.29
    сятся
    -1.28
     piel
    -1.27
    räder
    -1.26
     刺繍
    -1.24
    izienz
    -1.23
    Toponymie
    -1.23
    POSITIVE LOGITS
    '
    2.02
    錞
    1.52
    <td>
    1.50
    logrus
    1.48
     gewähr
    1.41
    
    1.39
    人气
    1.36
    __[
    1.34
     suyo
    1.33
     lone
    1.31
    Activations Density 0.054%

    No Known Activations