© 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. 78051
    Prev
    Next
    INDEX
    Explanations

    program keywords and code comments

    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
     août
    -0.93
    Видео
    -0.84
    complexType
    -0.82
    考えて
    -0.80
    Źródło
    -0.79
    //---
    -0.78
    amment
    -0.78
     atu
    -0.77
    Seleccion
    -0.77
    Здравствуйте
    -0.76
    POSITIVE LOGITS
    private
    0.96
    leg
    0.88
     zurückge
    0.85
    protected
    0.84
     erfolgen
    0.82
     welcomed
    0.82
    aked
    0.81
     a
    0.81
     recess
    0.81
     cérebro
    0.81
    Activations Density 0.002%

    No Known Activations