© 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. 14843
    Prev
    Next
    INDEX
    Explanations

    programming sleep calls

    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
    payers
    2.03
    า
    2.02
    廠
    2.02
    ه
    1.96
     outfile
    1.94
    iados
    1.92
     bỏ
    1.91
    ০০
    1.90
    ી
    1.89
    ி
    1.89
    POSITIVE LOGITS
     Kähler
    1.92
     Harb
    1.85
    दीश
    1.84
     Mank
    1.82
    cker
    1.81
     trasc
    1.81
    ๊ะ
    1.81
     declining
    1.80
     jeans
    1.78
    𝕚
    1.76
    Activations Density 0.022%

    No Known Activations