© 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. 34-GEMMASCOPE-RES-131K
    7. 78731
    Prev
    Next
    INDEX
    Explanations

    introduces topic of

    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_34/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
     erstes
    -1.01
     that
    -0.96
    xty
    -0.96
    HostException
    -0.94
     elevado
    -0.91
     См
    -0.89
     アクセサリー
    -0.85
     fría
    -0.85
    latter
    -0.85
     sánh
    -0.85
    POSITIVE LOGITS
     and
    0.89
     puberty
    0.80
    Слайд
    0.80
    そして
    0.79
    УДК
    0.73
    Enroll
    0.72
    enrollment
    0.72
     ext
    0.71
    Начало
    0.70
    Gön
    0.70
    Activations Density 0.005%

    No Known Activations