© 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. 1991
    Prev
    Next
    INDEX
    Explanations

    just paste

    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
    م
    2.11
    จัย
    1.88
    -
    1.85
    sum
    1.85
    -‘
    1.82
    cash
    1.81
     sum
    1.78
    m
    1.77
     עס
    1.76
    app
    1.73
    POSITIVE LOGITS
     preciso
    3.20
     Fleurit
    3.19
     ImageTk
    3.11
     algéb
    3.09
     gonflement
    3.06
    পত্র
    3.04
     indiquer
    3.00
    ഴിലാ
    2.96
    ড়িত
    2.96
     latar
    2.95
    Activations Density 0.083%

    No Known Activations