© 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. 22-GEMMASCOPE-RES-131K
    7. 26309
    Prev
    Next
    INDEX
    Explanations

    kitchen counter serving areas

    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_22/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
     Temos
    -1.13
     Konkurrenz
    -1.09
    噠
    -1.06
     този
    -1.05
     Mitteln
    -1.04
     минуты
    -1.03
    indest
    -1.03
     zumindest
    -0.99
     Ausrüstung
    -0.99
     Tries
    -0.98
    POSITIVE LOGITS
     argento
    1.41
     decisión
    1.31
     sentra
    1.29
     robuste
    1.25
     participe
    1.22
     brune
    1.20
     interieur
    1.19
     silueta
    1.19
     is
    1.18
    чке
    1.17
    Activations Density 0.005%

    No Known Activations