© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13657
    Prev
    Next
    INDEX
    Explanations

    gracefully, flights, Flying, frameworks, Mit, repetitions, grace, claim, vert, Contracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    то
    0.92
    2
    0.88
    0
    0.87
    с
    0.84
    define
    0.77
    1
    0.77
    pdb
    0.75
    txt
    0.73
    toc
    0.73
    or
    0.73
    POSITIVE LOGITS
    λεί
    0.91
     Broncos
    0.87
    RELATIVA
    0.86
     efectuar
    0.86
     Knicks
    0.86
     အမျိုး
    0.86
     psyche
    0.85
    🏙
    0.84
     Louvre
    0.84
     Bugünkü
    0.84
    Activations Density 0.000%

    No Known Activations