© 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. 112533
    Prev
    Next
    INDEX
    Explanations

    official speakers and persons

    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
     been
    -1.31
     my
    -1.28
    сал
    -1.21
     $
    -1.20
     nueve
    -1.20
     quatro
    -1.16
    
    -1.13
    I
    -1.13
    <bos>
    -1.10
     was
    -1.10
    POSITIVE LOGITS
    ῎
    1.42
    狆
    1.41
     contenir
    1.40
    ectin
    1.31
     fiabilidad
    1.30
    ﹶ
    1.27
     compared
    1.27
    лений
    1.26
    olische
    1.26
    捯
    1.24
    Activations Density 0.017%

    No Known Activations