© 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. 127792
    Prev
    Next
    INDEX
    Explanations

    location-based services

    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
     now
    -2.03
     after
    -1.58
     last
    -1.49
     from
    -1.38
     then
    -1.36
    </b>
    -1.32
     sidste
    -1.31
     jessica
    -1.29
     “
    -1.26
     because
    -1.26
    POSITIVE LOGITS
     we
    1.68
     ofrecerte
    1.43
     zult
    1.43
    Läh
    1.35
     you
    1.34
     ceux
    1.33
    Outras
    1.30
     pierws
    1.30
     كيفية
    1.30
    可能です
    1.29
    Activations Density 0.088%

    No Known Activations