© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43462
    Prev
    Next
    INDEX
    Explanations

    mommy juice, ATTORNEY GENERAL, systemctl

    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
    蚣
    -2.78
     dekoratif
    -2.77
     disiplin
    -2.50
     افغانستان
    -2.48
     expérience
    -2.44
    𝟭
    -2.44
     metode
    -2.42
     ordre
    -2.41
    чені
    -2.34
     groupe
    -2.33
    POSITIVE LOGITS
    ’
    3.38
    ing
    2.97
    an
    2.66
     trânsito
    2.63
    即便是
    2.61
     Glaube
    2.58
    ”
    2.58
     która
    2.58
    u
    2.55
     emprego
    2.53
    Activations Density 0.001%

    No Known Activations