© 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-16K
    7. 8567
    Prev
    Next
    INDEX
    Explanations

    mixing bowl creations

    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
     ،
    1.21
    Scientists
    1.13
    scientists
    1.11
     scientists
    1.09
    lll
    1.07
     علماء
    1.04
     Scientists
    1.04
    ‚
    1.04
    Vocabulary
    1.03
     ,
    1.02
    POSITIVE LOGITS
     conséqu
    1.37
     necessária
    1.35
     ebenfalls
    1.35
     necessários
    1.34
     necessário
    1.34
     aisément
    1.33
     obligación
    1.32
    ränkt
    1.32
     añad
    1.31
     sämt
    1.30
    Activations Density 0.295%

    No Known Activations