© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16277
    Prev
    Next
    INDEX
    Explanations

    memory buffer and chunk

    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
     all
    -1.15
     nemici
    -1.11
     on
    -1.10
     the
    -0.99
     those
    -0.98
     and
    -0.98
     aspetti
    -0.98
     OF
    -0.97
     models
    -0.96
     -
    -0.94
    POSITIVE LOGITS
     caracteres
    1.16
     enthousi
    1.14
    odendron
    1.13
    bourhood
    1.08
    
    1.05
    ásticos
    1.03
     vanille
    1.03
     BorderLayout
    1.03
     surpris
    1.03
    набор
    1.02
    Activations Density 0.010%

    No Known Activations