© 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. 425
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    om
    1.20
    ast
    1.19
    磡
    1.05
    ost
    1.02
    meed
    1.02
    ing
    1.01
    og
    1.01
    builder
    0.99
    ullar
    0.99
    țional
    0.98
    POSITIVE LOGITS
    円以上
    1.45
    ″]
    1.36
    CTIONS
    1.36
    גיע
    1.33
    ದುಕೊಳ್ಳ
    1.30
     Characters
    1.30
    的的
    1.30
    ธุ์
    1.30
     रमेश
    1.30
     RECORDS
    1.29
    Activations Density 1.234%

    No Known Activations