© 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. 158840
    Prev
    Next
    INDEX
    Explanations

    quantifying things

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

    excessive amounts or explanations

    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
     νέα
    0.50
    ibilité
    0.48
    indra
    0.48
    imia
    0.47
    irà
    0.46
    irk
    0.46
    éri
    0.45
    鴻
    0.45
    财务
    0.45
    ïs
    0.44
    POSITIVE LOGITS
     chaper
    0.49
    साना
    0.48
    करने
    0.47
     pollination
    0.47
     پرت
    0.47
     spearheaded
    0.46
     చేసే
    0.44
     rained
    0.44
     लड़ने
    0.43
     caramelized
    0.43
    Activations Density 0.000%

    No Known Activations