© 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. 15394
    Prev
    Next
    INDEX
    Explanations

    end of documents or code

    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
    '
    -1.33
     a
    -1.06
     Mesin
    -1.05
     Græ
    -1.03
     rezept
    -1.02
     ngunit
    -0.99
     vider
    -0.97
     comunale
    -0.97
    ’
    -0.92
     Daerah
    -0.91
    POSITIVE LOGITS
     and
    1.21
    erobic
    1.18
     способы
    1.16
     lägga
    1.16
     känna
    1.15
     äta
    1.15
     säga
    1.13
     lära
    1.13
     börja
    1.13
     läsa
    1.13
    Activations Density 0.003%

    No Known Activations