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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2013
    Prev
    Next
    INDEX
    Explanations

    before taking action or steps

    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
    Not in Any Lists

    No Comments

    Negative Logits
    යින්
    3.00
    forRoot
    2.74
    ৃদ
    2.72
    sman
    2.51
    ය
    2.43
    ла
    2.38
    යක්
    2.38
    os
    2.34
    ाय
    2.31
    یان
    2.28
    POSITIVE LOGITS
    毖
    2.55
    صول
    2.37
     wis
    2.37
    DrawerToggle
    2.35
     pojav
    2.34
    ণ্ডল
    2.33
     sebelum
    2.31
    ں
    2.31
    擞
    2.30
     judgements
    2.29
    Activations Density 0.192%

    No Known Activations