© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 420
    Prev
    Next
    INDEX
    Explanations

    ADTs, mechanisms, stability, adaptation

    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_22_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
     Для
    0.66
    შე
    0.64
    ка
    0.60
    вЂ
    0.59
    Ра
    0.58
    cable
    0.58
    н
    0.57
    эф
    0.57
     علي
    0.57
     ৩৩
    0.57
    POSITIVE LOGITS
     konkre
    0.69
     allerlei
    0.67
     lokale
    0.67
     optimale
    0.61
     prakt
    0.58
     aktivit
    0.57
     enorme
    0.57
     kreat
    0.57
     praktische
    0.56
     publik
    0.56
    Activations Density 0.181%

    No Known Activations