© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    occupations and job titles

    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
    们的
    1.80
    ท
    1.58
     ท
    1.52
    们
    1.46
    দের
    1.32
     ล
    1.29
     boş
    1.28
    şa
    1.27
    อำ
    1.27
     kteří
    1.24
    POSITIVE LOGITS
     formatted
    1.52
    withProperties
    1.48
    <unused733>
    1.46
    <unused1834>
    1.45
    <unused2032>
    1.44
     federally
    1.44
    ,|\
    1.44
     በዚህ
    1.43
    ziehungen
    1.41
     congru
    1.41
    Activations Density 0.286%

    No Known Activations