© 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. 21559
    Prev
    Next
    INDEX
    Explanations

    after following an event

    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
    -3.08
    、“
    -1.87
     these
    -1.80
     when
    -1.79
     белая
    -1.77
    呦
    -1.74
     unforeseen
    -1.73
    澳大利亚
    -1.72
    מים
    -1.70
     they
    -1.69
    POSITIVE LOGITS
     and
    1.94
    姽
    1.73
     uhd
    1.72
    輒
    1.70
    capulco
    1.65
    ちん
    1.65
    orithm
    1.61
    tification
    1.61
    uteurs
    1.59
    nachron
    1.59
    Activations Density 0.067%

    No Known Activations