© 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-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3027
    Prev
    Next
    INDEX
    Explanations

    point / number / gl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     মহল
    0.63
    Ꭹ
    0.61
     ಮು
    0.59
    RoutingModule
    0.59
    pegno
    0.58
     컬
    0.58
    webstore
    0.58
    rimazole
    0.58
     gas
    0.58
    喬
    0.57
    POSITIVE LOGITS
     Einst
    0.62
    ervation
    0.59
     transforma
    0.58
    uper
    0.58
     هت
    0.57
     له
    0.57
    くれて
    0.57
     toep
    0.57
    erva
    0.56
     Ist
    0.54
    Activations Density 0.106%

    No Known Activations