© 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. 99219
    Prev
    Next
    INDEX
    Explanations

    proper 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
     for
    -1.74
     esimerkiksi
    -1.46
    0
    -1.46
    2
    -1.45
     zrobić
    -1.36
    んでも
    -1.35
    for
    -1.29
     її
    -1.26
     για
    -1.26
     $-
    -1.26
    POSITIVE LOGITS
     wasn
    1.50
     was
    1.45
     SEMESTER
    1.44
     péro
    1.43
     himself
    1.37
    umente
    1.33
    直至
    1.30
     combustível
    1.30
     однако
    1.27
     silêncio
    1.27
    Activations Density 0.245%

    No Known Activations