© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14084
    Prev
    Next
    INDEX
    Explanations

    ethnic groups

    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
     m
    2.52
    olol
    2.46
    िवारी
    2.41
     চেয়ার
    2.40
     committed
    2.39
    륨
    2.37
     grounded
    2.36
    iously
    2.34
     sovereignty
    2.33
    ške
    2.32
    POSITIVE LOGITS
    ب
    2.90
    meat
    2.74
    اء
    2.44
    ي
    2.40
    ඟ
    2.35
    ੌ
    2.32
    ডিট
    2.31
    me
    2.30
    ger
    2.28
    ਦ
    2.28
    Activations Density 0.002%

    No Known Activations