© 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. 10765
    Prev
    Next
    INDEX
    Explanations

    css text-decoration property

    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
    ي
    1.12
    atlan
    1.10
    that
    1.06
    .–
    1.04
     acumen
    1.03
    neighborhood
    1.02
    although
    1.02
    hooter
    1.01
    in
    1.00
    nexus
    0.99
    POSITIVE LOGITS
    Ộ
    1.37
    錡
    1.32
    Ọ
    1.31
    гом
    1.28
    Ř
    1.26
    ions
    1.24
    świę
    1.24
    埝
    1.20
    álně
    1.19
    𝚆
    1.19
    Activations Density 0.035%

    No Known Activations