© 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. 618
    Prev
    Next
    INDEX
    Explanations

    degrees of intensity or progression

    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
    ر
    3.50
    ని
    2.71
    町村
    2.62
    嗘
    2.57
    खिल
    2.55
    تع
    2.52
    мә
    2.44
    嗗
    2.39
    \"",
    2.39
    ل
    2.39
    POSITIVE LOGITS
    𝗵
    2.95
    𝗲
    2.86
    𝗮
    2.85
    𝘂
    2.79
    𝗱
    2.74
    𝗿
    2.59
    𝗻
    2.50
    𝗹
    2.46
    𝗶
    2.39
    𝘃
    2.37
    Activations Density 0.777%

    No Known Activations