© 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. 99966
    Prev
    Next
    INDEX
    Explanations

    critical thinking

    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
     the
    -2.06
     that
    -1.91
     cercano
    -1.64
     vuo
    -1.63
     famoso
    -1.54
     minuman
    -1.44
     réglementation
    -1.43
    ↵
    -1.41
     kaas
    -1.38
     zowel
    -1.38
    POSITIVE LOGITS
    鋮
    1.74
    これは
    1.51
     осуществляется
    1.45
    zzazione
    1.44
    SURFACE
    1.39
    ilités
    1.38
     жена
    1.38
    acuation
    1.37
    Those
    1.36
    ጴ
    1.36
    Activations Density 0.017%

    No Known Activations