© 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. 59310
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     parfois
    -1.88
     الإنسان
    -1.64
     取り付け
    -1.63
     cependant
    -1.56
     حتی
    -1.55
     pueden
    -1.55
     掃除
    -1.54
     thoſe
    -1.52
    ↵
    -1.51
    ſo
    -1.51
    POSITIVE LOGITS
     this
    2.61
     it
    2.11
     during
    1.73
     on
    1.70
     after
    1.67
     ciudadana
    1.58
     went
    1.55
     mainly
    1.55
    They
    1.54
     camión
    1.52
    Activations Density 0.011%

    No Known Activations