© 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. 48746
    Prev
    Next
    INDEX
    Explanations

    Swedish and English 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
     beantragt
    -0.96
     beschlossen
    -0.93
     versucht
    -0.92
     Versammlung
    -0.92
     gezwungen
    -0.91
     ему
    -0.90
     annehmen
    -0.85
    (!__
    -0.85
     ausgeschlossen
    -0.82
     veniva
    -0.82
    POSITIVE LOGITS
     have
    1.20
     has
    0.90
     lilla
    0.86
     måte
    0.86
     pisau
    0.86
     åren
    0.85
     certainty
    0.85
    CHANNELS
    0.85
     antik
    0.84
    TINGS
    0.84
    Activations Density 0.022%

    No Known Activations