© 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. 71156
    Prev
    Next
    INDEX
    Explanations

    leaving a comment or reply

    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
     balas
    -1.66
     durer
    -1.54
    Its
    -1.48
     legenda
    -1.45
     pantalon
    -1.45
     regata
    -1.44
     kado
    -1.43
     soldat
    -1.41
     kela
    -1.40
    INAR
    -1.38
    POSITIVE LOGITS
     an
    2.03
     any
    1.52
     потім
    1.49
     a
    1.46
     protože
    1.44
    了他
    1.40
    他說
    1.38
    </strong>
    1.30
    くださった
    1.26
    匱
    1.26
    Activations Density 0.013%

    No Known Activations