© 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. 10687
    Prev
    Next
    INDEX
    Explanations

    spare tire and parts

    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
    𝑒
    2.34
    س
    2.20
     گھر
    2.10
    ческого
    2.05
    illah
    2.03
    েই
    2.03
    াচার
    2.02
    ীদের
    2.01
     ‘
    2.01
    asının
    2.00
    POSITIVE LOGITS
    絊
    2.64
    𝚊
    2.49
    絴
    2.40
    ,'"
    2.39
    ᆷ
    2.32
     loose
    2.31
    絟
    2.30
    𝚏
    2.27
    𝙰
    2.25
    (";
    2.24
    Activations Density 0.041%

    No Known Activations