© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14765
    Prev
    Next
    INDEX
    Explanations

    with food items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    1.22
    the
    1.22
    stå
    1.21
    chemical
    1.19
     hadi
    1.18
    नाम
    1.16
     legislação
    1.12
    粒
    1.12
    st
    1.11
    th
    1.10
    POSITIVE LOGITS
     Get
    1.39
     get
    1.36
    MFC
    1.34
    ্ম্ম
    1.33
     endure
    1.32
    靂
    1.30
     کس
    1.28
     Gets
    1.28
     Absolutely
    1.28
     achieve
    1.27
    Activations Density 0.005%

    No Known Activations