© 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. 3610
    Prev
    Next
    INDEX
    Explanations

    HTTPS Everywhere

    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
    spacerItem
    1.28
    ulative
    1.26
    Цент
    1.23
    شمند
    1.20
    捉
    1.19
    Vik
    1.17
    위를
    1.14
     Jesuits
    1.12
    ships
    1.11
    덥
    1.10
    POSITIVE LOGITS
    에
    1.48
    に
    1.41
    lej
    1.35
     strictly
    1.30
    hipping
    1.29
    联赛
    1.25
    ్యం
    1.23
    wani
    1.22
    tosecond
    1.21
    жок
    1.20
    Activations Density 0.035%

    No Known Activations