© 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. 102749
    Prev
    Next
    INDEX
    Explanations

    easy steps to

    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
    <0xF4>
    -1.24
     Ofrece
    -1.23
    虓
    -1.23
    那么
    -1.21
    譏
    -1.19
    )_{\
    -1.15
     Descubre
    -1.14
     Saffron
    -1.13
     
    -1.12
     самому
    -1.11
    POSITIVE LOGITS
     because
    1.55
     at
    1.40
     also
    1.39
     had
    1.36
     only
    1.34
     кількість
    1.33
     this
    1.27
     these
    1.26
     not
    1.25
     if
    1.25
    Activations Density 0.356%

    No Known Activations