© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13789
    Prev
    Next
    INDEX
    Explanations

    AI21 Labs

    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_7_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
     spoonful
    2.00
    ി
    1.95
    ይ
    1.80
    ing
    1.75
    აზ
    1.74
    ordable
    1.73
    e
    1.63
    apurna
    1.63
    igera
    1.62
     sweetness
    1.62
    POSITIVE LOGITS
     Thiết
    2.30
    ności
    2.06
    엔
    2.05
    槤
    2.04
     спів
    2.01
    儡
    1.99
    瘓
    1.96
     nghĩa
    1.96
     июля
    1.95
     références
    1.94
    Activations Density 0.064%

    No Known Activations