© 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. 77703
    Prev
    Next
    INDEX
    Explanations

    code associations and imports

    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
     Inscription
    -0.81
    onResume
    -0.81
    paux
    -0.80
     divine
    -0.79
    yttää
    -0.78
    供应
    -0.78
    UserController
    -0.78
    꿇
    -0.76
    helm
    -0.76
    ITES
    -0.75
    POSITIVE LOGITS
    WithMany
    0.85
     via
    0.79
     pensée
    0.78
    胧
    0.77
    标记
    0.77
     میں
    0.72
     Rather
    0.71
     tenía
    0.71
     حيث
    0.70
     ביותר
    0.70
    Activations Density 0.004%

    No Known Activations