© 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. 112247
    Prev
    Next
    INDEX
    Explanations

    us vs them

    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
     their
    -1.97
     because
    -1.58
     kommune
    -1.54
     gård
    -1.46
     each
    -1.44
     some
    -1.38
     regarding
    -1.38
     using
    -1.35
     that
    -1.34
     what
    -1.34
    POSITIVE LOGITS
     don
    1.66
    usually
    1.63
    It
    1.61
     are
    1.60
    typically
    1.57
    especially
    1.52
    ୬
    1.52
     tiefe
    1.52
    更に
    1.52
    generally
    1.49
    Activations Density 0.013%

    No Known Activations