© 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. 128990
    Prev
    Next
    INDEX
    Explanations

    Canada

    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
    }
    -3.41
     ,"
    -2.86
     -"
    -2.83
    
    -2.81
     reempla
    -2.70
    𐬹
    -2.58
     :"
    -2.58
    </h3>
    -2.55
    菡
    -2.55
    </strong>
    -2.53
    POSITIVE LOGITS
    Nearly
    3.02
    Many
    2.98
    $
    2.89
    鸯
    2.89
    Since
    2.88
    Almost
    2.86
    Because
    2.86
    Several
    2.81
    Before
    2.80
    With
    2.78
    Activations Density 0.014%

    No Known Activations