© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 713
    Prev
    Next
    INDEX
    Explanations

    numbered lists and quantities

    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_65k_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
     várias
    1.49
     muitos
    1.45
     muitas
    1.45
     muchas
    1.38
    ‪
    1.36
     nombreuses
    1.35
     viele
    1.32
     muito
    1.31
     algumas
    1.30
     vários
    1.28
    POSITIVE LOGITS
     shortage
    1.19
     hurdle
    1.11
     exploratory
    1.10
     survey
    1.09
     청
    1.07
     introductory
    1.05
     barrier
    1.05
     replacement
    1.04
     truce
    1.04
     supplemental
    1.04
    Activations Density 0.697%

    No Known Activations