© 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. 644
    Prev
    Next
    INDEX
    Explanations

    article and preposition phrases

    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
    ism
    2.03
    R
    1.84
    P
    1.80
    C
    1.73
    S
    1.72
    ve
    1.61
    ote
    1.61
    )
    1.60
    ary
    1.59
    L
    1.54
    POSITIVE LOGITS
    LOTREntity
    2.35
    rparam
    2.25
     nirvach
    2.23
    𒄐
    2.19
    <unused846>
    2.16
    <unused873>
    2.12
     oln
    2.10
    此之外
    2.09
    <unused786>
    2.06
    AppBsky
    2.05
    Activations Density 0.914%

    No Known Activations