© 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. 26599
    Prev
    Next
    INDEX
    Explanations

    programmatic variable assignments

    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
     bluz
    -1.07
     lavadora
    -1.05
     trafik
    -1.02
     mikrofon
    -1.01
    كويكب
    -1.00
     ansik
    -1.00
     paket
    -0.98
     mépris
    -0.98
    telefon
    -0.97
     ihan
    -0.97
    POSITIVE LOGITS
     as
    1.23
     it
    1.03
     by
    0.94
     keep
    0.90
     even
    0.89
     they
    0.88
     make
    0.88
     said
    0.87
     most
    0.87
     think
    0.86
    Activations Density 0.025%

    No Known Activations