© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1151
    Prev
    Next
    INDEX
    Explanations

    feed-forward neural networks

    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
     Ven
    1.24
     지급
    1.20
     fi
    1.17
    ’
    1.16
     ME
    1.13
     ’
    1.10
    usses
    1.09
     meg
    1.08
     灯
    1.08
     Code
    1.08
    POSITIVE LOGITS
    globalMap
    1.41
    SqlQuery
    1.41
    ᵏ
    1.35
    turno
    1.32
     возможно
    1.32
    fuzzy
    1.27
    Much
    1.26
    Jordan
    1.25
    Asimismo
    1.24
    જ
    1.23
    Activations Density 0.012%

    No Known Activations