© 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. 40152
    Prev
    Next
    INDEX
    Explanations

    the followed by specific noun

    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
    ⎔
    -1.81
    鼯
    -1.75
    丝毫
    -1.68
    beit
    -1.65
     condam
    -1.65
    ":"+
    -1.63
    ksiyon
    -1.60
    sten
    -1.59
    knows
    -1.59
     mañana
    -1.56
    POSITIVE LOGITS
     each
    2.52
     our
    1.72
     following
    1.65
     different
    1.64
     currently
    1.59
     now
    1.59
     Käufer
    1.59
    untut
    1.57
     stället
    1.55
     To
    1.52
    Activations Density 0.110%

    No Known Activations