© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 250
    Prev
    Next
    INDEX
    Explanations

    Finance, commerce, sales, bureaus

    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_13_width_65k_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
     שנים
    0.89
     гораздо
    0.87
     Harp
    0.87
    ֤
    0.85
     biru
    0.81
    许多
    0.81
     بسیاری
    0.80
    çok
    0.79
    ानीय
    0.79
    bund
    0.79
    POSITIVE LOGITS
     وإ
    1.16
     audiov
    1.15
     variáveis
    1.09
     Extra
    1.09
     والإ
    1.08
     Simplify
    1.07
     и
    1.06
     autón
    1.03
     corresponds
    1.03
     ולה
    1.02
    Activations Density 0.000%

    No Known Activations