© 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. 59754
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    xvii
    -1.79
     you
    -1.56
     and
    -1.53
    xiii
    -1.49
    Sx
    -1.48
    %";
    -1.44
    
    -1.41
    ϑ
    -1.38
    -1.38
     its
    -1.37
    POSITIVE LOGITS
    他の
    2.17
    2
    1.92
    These
    1.84
    4
    1.79
    Their
    1.66
    6
    1.63
    Other
    1.62
    Others
    1.59
     вместо
    1.56
    Partager
    1.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.