© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100956
    Prev
    Next
    INDEX
    Explanations

    speed and pace

    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
     plă
    -1.67
     urmă
    -1.63
     Seem
    -1.60
     erstes
    -1.56
    妺
    -1.48
     wykon
    -1.48
     hecha
    -1.43
     \
    -1.41
    ՚
    -1.41
     Fairly
    -1.40
    POSITIVE LOGITS
     doesn
    1.87
     asio
    1.70
     برانيه
    1.66
     esses
    1.65
     our
    1.56
     }^{*}
    1.55
     essas
    1.55
    我们的
    1.51
     weren
    1.49
     pace
    1.48
    Activations Density 0.018%

    No Known Activations