© 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. 7135
    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
    🤨
    -1.74
    cessed
    -1.73
    nibal
    -1.73
    😳
    -1.67
    😲
    -1.66
    »?
    -1.66
    "^
    -1.65
    😬
    -1.65
    🤞
    -1.64
    🤑
    -1.64
    POSITIVE LOGITS
     our
    1.80
    说完
    1.73
    of
    1.71
     I
    1.62
    ではまた
    1.58
     your
    1.55
     should
    1.55
     also
    1.53
     sambil
    1.48
    Of
    1.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.