© 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. 14122
    Prev
    Next
    INDEX
    Explanations

    roman numeral section markers

    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
    wu
    1.23
    2
    1.21
    té
    1.19
    utes
    1.18
    Lemma
    1.16
    iffer
    1.12
    当該
    1.11
    #
    1.11
    £
    1.10
    4
    1.09
    POSITIVE LOGITS
    经典的
    1.78
    𝙿
    1.78
     άνθρω
    1.76
     nascimento
    1.75
    𝚂
    1.74
     ancients
    1.65
    ोध
    1.64
     древ
    1.62
     cartas
    1.62
     นา
    1.62
    Activations Density 0.080%

    No Known Activations