© 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. 113821
    Prev
    Next
    INDEX
    Explanations

    quantifiers of nouns

    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
    嫫
    -1.61
     to
    -1.59
     они
    -1.56
    魉
    -1.53
    ",
    -1.52
    '),
    -1.43
    емость
    -1.39
     Они
    -1.37
     We
    -1.36
     ellos
    -1.36
    POSITIVE LOGITS
     would
    1.63
     you
    1.50
     could
    1.49
    mahaman
    1.44
     municipalité
    1.40
     Kedua
    1.35
     ว่า
    1.33
     Tetapi
    1.31
     differentiates
    1.30
    広告
    1.29
    Activations Density 0.113%

    No Known Activations