© 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. 14318
    Prev
    Next
    INDEX
    Explanations

    describing categorize cultures China sight focus plan mass

    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
     bothering
    0.80
     telas
    0.76
    یہ
    0.75
    纭
    0.75
     відповіда
    0.74
     साधा
    0.74
    ့်
    0.73
     ін
    0.73
     produzione
    0.72
     lakukan
    0.72
    POSITIVE LOGITS
    ())){
    0.74
     flank
    0.69
     prazer
    0.69
     cep
    0.67
    ()){
    0.66
     vegan
    0.66
    ఙ
    0.66
    paid
    0.65
    ヴェ
    0.65
     VES
    0.65
    Activations Density 0.000%

    No Known Activations