© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14989
    Prev
    Next
    INDEX
    Explanations

    angular core or momentum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    р
    2.75
     darn
    2.33
    으로
    2.10
    ्त
    2.07
    й
    2.04
    ット
    2.03
    У
    2.03
    ्
    2.02
     koja
    1.99
    ﺎ
    1.99
    POSITIVE LOGITS
    %>%
    2.70
    㸮
    2.66
    rijke
    2.61
    erus
    2.58
     accusing
    2.45
    {&
    2.40
    erent
    2.37
     pertain
    2.30
    ➔
    2.30
     Mathf
    2.25
    Activations Density 0.073%

    No Known Activations