© 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. 127848
    Prev
    Next
    INDEX
    Explanations

    cause and effect relationships

    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
     other
    -2.06
     various
    -1.61
     or
    -1.53
     which
    -1.50
     уважением
    -1.48
     many
    -1.46
     вместо
    -1.46
     zahlreichen
    -1.45
     several
    -1.45
    не
    -1.39
    POSITIVE LOGITS
     however
    2.45
     jedoch
    1.84
     però
    1.71
     však
    1.63
     infatti
    1.59
     inoltre
    1.55
    饜
    1.53
    もありますが
    1.52
    却不
    1.50
     kuitenkin
    1.46
    Activations Density 1.406%

    No Known Activations