© 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. 72752
    Prev
    Next
    INDEX
    Explanations

    user directory paths

    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
     that
    -1.44
    の概要
    -1.21
     a
    -1.19
     from
    -1.18
    latimes
    -1.16
    任何
    -1.16
     between
    -1.14
    waitKey
    -1.14
     such
    -1.13
     andere
    -1.13
    POSITIVE LOGITS
     Obtén
    1.19
     nôtre
    1.15
    cedores
    1.08
    そこで
    1.06
    Producción
    1.05
    ٥
    1.05
    ever
    1.03
     Erdoğan
    1.00
    Debido
    1.00
     epitome
    1.00
    Activations Density 0.006%

    No Known Activations