© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3917
    Prev
    Next
    INDEX
    Explanations

    you followed by punctuation or you

    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
    Negative Logits
    ให้บริการ
    1.50
     在
    1.50
     ภาษา
    1.47
     일반적으로
    1.46
     모양
    1.43
    ฺ
    1.40
     功能
    1.38
     如
    1.38
     넓
    1.37
    غة
    1.37
    POSITIVE LOGITS
     venced
    1.76
     tentativas
    1.75
     prévenir
    1.60
     pelea
    1.60
    ोर्ट
    1.57
    getTeam
    1.57
    খ্যা
    1.56
     dirigeants
    1.55
     derrot
    1.54
     sconf
    1.53
    Activations Density 0.278%

    No Known Activations