© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10858
    Prev
    Next
    INDEX
    Explanations

    atmosphere and its properties

    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
    ljenje
    2.24
    ané
    2.05
    氛围
    2.03
    axy
    2.02
    uhi
    2.01
    perluan
    2.00
    Ꮕ
    1.98
     kompleks
    1.96
     dior
    1.91
    ীষ
    1.90
    POSITIVE LOGITS
    жить
    2.10
    굳
    2.01
    န့်
    1.89
     Indices
    1.81
    &-
    1.81
    ্ভব
    1.79
    \%$
    1.78
    friendly
    1.75
     suppression
    1.75
     ngừng
    1.75
    Activations Density 0.005%

    No Known Activations