© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 74233
    Prev
    Next
    INDEX
    Explanations

    life roles and responsibilities

    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
     for
    -2.72
     and
    -2.20
     of
    -1.97
     in
    -1.88
     at
    -1.83
     that
    -1.80
     also
    -1.77
     from
    -1.76
     with
    -1.66
     on
    -1.57
    POSITIVE LOGITS
    这人
    1.52
    俢
    1.49
    יוון
    1.45
     reason
    1.32
    了许多
    1.30
    Hmmm
    1.28
     العديد
    1.27
    Profes
    1.27
     pertinente
    1.27
     vegano
    1.26
    Activations Density 0.165%

    No Known Activations