© 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. 12404
    Prev
    Next
    INDEX
    Explanations

    numerical fractions

    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
     Midwest
    1.07
     Center
    1.01
     School
    1.00
    K
    0.97
     hometown
    0.96
     Company
    0.96
     theater
    0.95
    ↵
    0.94
     vacation
    0.93
     County
    0.93
    POSITIVE LOGITS
    𝚎
    1.54
    㳒
    1.48
    𝚘
    1.42
     kahelaro
    1.41
     namani
    1.41
    <unused298>
    1.40
    ⚠
    1.40
    綀
    1.40
     tasmim
    1.40
    fnamefont
    1.40
    Activations Density 0.469%

    No Known Activations