© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8329
    Prev
    Next
    INDEX
    Explanations

    code formatting

    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
    или
    0.59
    ть
    0.57
    '),
    0.55
    ['
    0.55
    ],
    0.55
    =(
    0.55
    л
    0.55
                       
    0.54
    $,
    0.54
    ,'
    0.54
    POSITIVE LOGITS
     syk
    0.64
     hijo
    0.60
     কাকে
    0.57
    ப்பாடு
    0.55
     istilah
    0.55
     servici
    0.55
     sederhana
    0.54
    िसो
    0.54
     eenvoud
    0.54
     acronym
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.