© 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. 78389
    Prev
    Next
    INDEX
    Explanations

    colors and backgrounds

    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
    LEFT
    -0.88
     ayer
    -0.82
    ksa
    -0.82
    czerw
    -0.82
    KG
    -0.82
    jestel
    -0.82
     Pilates
    -0.82
    
    -0.81
    ccini
    -0.81
    RIER
    -0.81
    POSITIVE LOGITS
     adopt
    0.78
    Perú
    0.78
    ansvar
    0.74
     denkt
    0.73
    Huhu
    0.73
    Mixtures
    0.71
    ضات
    0.71
     operações
    0.70
     responsáveis
    0.69
    части
    0.69
    Activations Density 0.010%

    No Known Activations