© 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. 99979
    Prev
    Next
    INDEX
    Explanations

    as Newas Canadaas theas causein haltingon The

    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
     MotionEvent
    -1.39
     with
    -1.38
    forKey
    -1.35
     also
    -1.34
     marcado
    -1.30
     cuerdas
    -1.27
    cccccccc
    -1.27
     initWithFrame
    -1.27
     less
    -1.25
     doskon
    -1.25
    POSITIVE LOGITS
     the
    1.28
     potrebbe
    1.27
     aseguran
    1.26
    鶲
    1.26
     alberga
    1.23
     Kurse
    1.23
     podría
    1.23
     который
    1.23
     Preisen
    1.22
     meisten
    1.20
    Activations Density 0.026%

    No Known Activations