© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    deriving answers and formulas

    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
    ไง
    2.83
    রামর্শ
    2.77
    )(&
    2.68
     charity
    2.52
    বিত্র
    2.52
    Յ
    2.52
    ทาง
    2.51
     яким
    2.50
    ень
    2.49
     s
    2.49
    POSITIVE LOGITS
    ي
    3.09
    ا
    2.96
    amond
    2.67
    𝒋
    2.64
    sj
    2.60
    یی
    2.58
    dbo
    2.57
    𝒗
    2.54
    ozems
    2.50
    sina
    2.48
    Activations Density 0.003%

    No Known Activations