© 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. 10-GEMMASCOPE-RES-131K
    7. 128439
    Prev
    Next
    INDEX
    Explanations

    LaTeX and code keywords

    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
    </i>
    -2.03
     first
    -1.98
    .”
    -1.97
    ??
    -1.73
    ......
    -1.72
     may
    -1.68
    ....
    -1.68
     was
    -1.66
     "
    -1.66
     an
    -1.61
    POSITIVE LOGITS
    ⟣
    1.96
    ⧠
    1.77
    妧
    1.74
    monedas
    1.73
     模様
    1.72
    ícias
    1.70
    actéristi
    1.66
    medriver
    1.66
    
    1.63
     insanely
    1.63
    Activations Density 0.004%

    No Known Activations