© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 786
    Prev
    Next
    INDEX
    Explanations

    list and team context

    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
    ات
    2.86
    عرض
    2.46
    मर्रा
    2.42
    вая
    2.39
    পক্ষে
    2.35
    ্কা
    2.33
    ు
    2.33
    اتي
    2.30
     absoluto
    2.30
    क्त
    2.27
    POSITIVE LOGITS
     MEMBERS
    2.61
     members
    2.57
     Members
    2.51
    Members
    2.36
    members
    2.35
    wise
    2.13
     MEMBER
    2.13
     memberships
    2.07
    团
    2.03
     Member
    2.00
    Activations Density 0.864%

    No Known Activations