© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14269
    Prev
    Next
    INDEX
    Explanations

    varies from person to person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     उत्सा
    1.04
     அருக
    1.04
    ઠવા
    1.01
     purnama
    1.00
     adulte
    0.98
     closets
    0.97
     불안
    0.97
    淙
    0.94
    четов
    0.94
    দাম
    0.92
    POSITIVE LOGITS
    +","
    1.05
    די
    1.04
    මේ
    1.03
    compared
    1.02
    ುತ್ತದೆ
    1.01
    arab
    0.99
    Mai
    0.96
     compared
    0.95
    ඇ
    0.95
    Import
    0.90
    Activations Density 0.241%

    No Known Activations