© 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. 4829
    Prev
    Next
    INDEX
    Explanations

    brain and cognitive processes

    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
    uating
    1.27
    leqslant
    1.26
    腱
    1.21
    ెస్
    1.21
    ltimes
    1.20
    鎶
    1.19
     समर्
    1.19
    ************
    1.17
    ,((
    1.16
     asterisk
    1.16
    POSITIVE LOGITS
    ا
    1.19
     Expensive
    1.19
     contenidos
    1.15
    瘤
    1.14
    ozy
    1.10
    vic
    1.09
    漿
    1.09
    Expensive
    1.08
     Contains
    1.08
     Соответ
    1.08
    Activations Density 1.095%

    No Known Activations