© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75250
    Prev
    Next
    INDEX
    Explanations

    carry out actions

    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_10/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
    硨
    -2.05
     papillon
    -1.78
     flesta
    -1.74
    ਃ
    -1.70
     möj
    -1.69
    '__
    -1.67
    wnątrz
    -1.66
     only
    -1.66
     conseille
    -1.63
    鱟
    -1.63
    POSITIVE LOGITS
    </em>
    2.44
     You
    2.33
    </strong>
    2.08
    ximos
    1.95
     It
    1.88
     ‘
    1.86
     “
    1.72
    .”
    1.71
     This
    1.70
    ’,
    1.69
    Activations Density 0.008%

    No Known Activations