© 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. 136704
    Prev
    Next
    INDEX
    Explanations

    names, prize, credit, agreement, winner

    np_acts-logits-general · gemini-2.5-flash-lite

    Hispanic names

    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
    зже
    0.46
     mica
    0.45
    嫁
    0.45
     kernels
    0.44
     গুণ
    0.43
     expertise
    0.43
     parturient
    0.41
    ↵
    0.40
     artifacts
    0.40
     glycerol
    0.40
    POSITIVE LOGITS
    ্পনিক
    0.46
    કારે
    0.45
     പിന്തു
    0.43
    Hepin
    0.43
    ായി
    0.43
    اه
    0.42
    करने
    0.42
     differenza
    0.42
    ിക്കുന്നത്
    0.42
    Ан
    0.42
    Activations Density 0.001%

    No Known Activations