© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 238128
    Prev
    Next
    INDEX
    Explanations

    business, places, and travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     américaine
    0.54
     подели
    0.50
     অল
    0.50
     ameryka
    0.48
    Hyper
    0.48
     utan
    0.47
    entraînement
    0.47
    枌
    0.47
     τρί
    0.47
     অনুষ্ঠিত
    0.47
    POSITIVE LOGITS
     nasal
    0.47
     plasmid
    0.47
     seman
    0.46
     wards
    0.45
     UIAlert
    0.44
     जबाब
    0.43
     sufferers
    0.42
     पदार्थ
    0.42
     bland
    0.42
     beggar
    0.42
    Activations Density 0.001%

    No Known Activations