© 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. 25762
    Prev
    Next
    INDEX
    Explanations

    past references or specific instances

    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
     neuen
    -1.21
     già
    -1.05
     előtt
    -0.99
     reciente
    -0.99
     nuevas
    -0.98
     baru
    -0.95
     Already
    -0.95
     nuevos
    -0.94
     apareceu
    -0.93
     mới
    -0.93
    POSITIVE LOGITS
    あの
    1.77
     those
    1.77
     that
    1.70
     damals
    1.48
     उस
    1.40
    当时
    1.33
     تلك
    1.30
     aquel
    1.29
    那个
    1.26
     jener
    1.25
    Activations Density 0.058%

    No Known Activations