© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 4762
    Prev
    Next
    INDEX
    Explanations

    people's roles or states

    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_13_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
     and
    1.29
     of
    1.25
    .
    1.24
    /
    1.23
    ial
    1.16
    ,
    1.15
    (?)
    1.15
     standing
    1.12
     or
    1.08
    -
    1.03
    POSITIVE LOGITS
     tạo
    1.52
     possuem
    1.50
     ăn
    1.48
    ড়ায়
    1.46
     następnie
    1.46
     tumeurs
    1.44
     contiennent
    1.43
     dwRes
    1.41
     imaju
    1.41
     özellikleri
    1.40
    Activations Density 0.078%

    No Known Activations