© 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. 64647
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and variables

    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
    :✨
    -1.15
    fordshire
    -1.11
    ixante
    -1.05
    tvguidetime
    -1.05
    ıs
    -1.05
    logías
    -1.02
    arschu
    -1.00
     hitters
    -0.97
     trovato
    -0.96
    ztes
    -0.96
    POSITIVE LOGITS
     of
    0.98
     tradizionale
    0.96
    y
    0.96
     Substan
    0.95
    (
    0.94
    FFFFFF
    0.92
     femininos
    0.90
     treats
    0.90
     DISE
    0.89
     sicht
    0.89
    Activations Density 0.025%

    No Known Activations