© 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. 102628
    Prev
    Next
    INDEX
    Explanations

    a reference to another

    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
     artesanía
    -1.52
    :['
    -1.37
     facade
    -1.36
    」
    -1.34
    </h5>
    -1.30
    </b>
    -1.29
    啻
    -1.28
    ripsi
    -1.27
    idopsis
    -1.27
     caucho
    -1.26
    POSITIVE LOGITS
     that
    1.80
     these
    1.61
     the
    1.59
     those
    1.53
     things
    1.43
     aastal
    1.37
     âgé
    1.34
     kteří
    1.33
    רְ
    1.33
    那我
    1.32
    Activations Density 0.005%

    No Known Activations