© 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. 72385
    Prev
    Next
    INDEX
    Explanations

    `char **` in code

    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
     discer
    -1.45
     再
    -1.35
    lış
    -1.32
    它
    -1.29
     "
    -1.28
     使っ
    -1.27
     "..
    -1.25
     चल
    -1.23
     
    -1.22
     "'
    -1.20
    POSITIVE LOGITS
     industrielle
    1.51
    趿
    1.50
     habile
    1.48
    砹
    1.43
    dây
    1.41
     chimiques
    1.40
    ctility
    1.38
     anciennes
    1.34
     spirituelle
    1.34
     manuelle
    1.32
    Activations Density 0.002%

    No Known Activations