© 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. 1804
    Prev
    Next
    INDEX
    Explanations

    emphasis

    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
    浇
    1.59
     하기
    1.57
     lau
    1.54
    럼
    1.51
     आयोजन
    1.51
    𝙫
    1.50
     συ
    1.50
     पठान
    1.49
     ਦਵਾਈ
    1.49
    𝕤
    1.49
    POSITIVE LOGITS
     तरफ
    1.76
    MOST
    1.76
     جانب
    1.72
     последние
    1.71
    Ко
    1.65
     лицо
    1.64
    облада
    1.64
     посе
    1.63
     ओर
    1.62
     наиболее
    1.60
    Activations Density 0.080%

    No Known Activations