© 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. 8399
    Prev
    Next
    INDEX
    Explanations

    common structural words

    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
     that
    -1.85
     to
    -1.58
    ve
    -1.57
    казания
    -1.46
    X
    -1.44
    :
    -1.43
     be
    -1.42
    仪式
    -1.40
     overflowing
    -1.39
     開始
    -1.36
    POSITIVE LOGITS
    dáms
    1.69
     étant
    1.61
    Итак
    1.55
     bekämp
    1.52
    Angebot
    1.50
     parachoque
    1.49
    США
    1.48
    ꯷
    1.43
     Envelope
    1.42
    ientes
    1.41
    Activations Density 0.190%

    No Known Activations