© 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. 84134
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    ↵↵
    -1.63
     same
    -1.35
    in
    -1.33
     mediante
    -1.26
    jak
    -1.20
    aw
    -1.20
    tos
    -1.18
    u
    -1.17
    z
    -1.15
    em
    -1.14
    POSITIVE LOGITS
     that
    2.70
     for
    2.33
     or
    2.19
    hanno
    1.50
     which
    1.49
     daarvoor
    1.45
     bijvoorbeeld
    1.41
    engaruhi
    1.39
     uitgenodigd
    1.38
     odası
    1.38
    Activations Density 0.048%

    No Known Activations