© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130617
    Prev
    Next
    INDEX
    Explanations

    on the caseon the pageon top ofover theonto biggeron board withonto Mad Menbehind us

    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
    3
    -1.45
    What
    -1.41
     tomada
    -1.36
     gonzález
    -1.33
     from
    -1.32
    િક
    -1.27
    landır
    -1.27
     rękaw
    -1.26
    How
    -1.25
     Verhalten
    -1.22
    POSITIVE LOGITS
    нология
    1.70
    ){$
    1.57
    ani
    1.51
     they
    1.49
    踽
    1.47
     alent
    1.41
     tlie
    1.38
    >
    1.38
     innan
    1.37
     joc
    1.36
    Activations Density 0.023%

    No Known Activations