© 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. 80767
    Prev
    Next
    INDEX
    Explanations

    worth of quantity

    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
    猡
    -2.14
    鼙
    -1.80
    dersfield
    -1.72
    -1.64
     只
    -1.63
     unele
    -1.61
    dă
    -1.60
     problemi
    -1.58
    琲
    -1.55
     ventaja
    -1.55
    POSITIVE LOGITS
     of
    2.89
    </h3>
    1.97
    沨
    1.80
     the
    1.80
    s
    1.78
    </strong>
    1.69
    2
    1.69
     he
    1.68
    ,"
    1.66
    ៚
    1.66
    Activations Density 0.004%
    No Known Activations