© 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. 62956
    Prev
    Next
    INDEX
    Explanations

    scientific and technical phrases

    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
    vali
    -0.73
     into
    -0.73
    σετε
    -0.71
    websocket
    -0.71
    problema
    -0.70
     frågan
    -0.70
    algunos
    -0.69
    باب
    -0.68
     Cleopatra
    -0.68
    Modificar
    -0.67
    POSITIVE LOGITS
     partial
    0.93
     Partial
    0.93
    δ
    0.85
    時尚
    0.85
    Partial
    0.82
     δ
    0.79
    partial
    0.79
     polar
    0.75
     Polar
    0.74
    ]</
    0.73
    Activations Density 0.038%

    No Known Activations