© 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. 7390
    Prev
    Next
    INDEX
    Explanations

    event management and architecture

    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
    ปรับ
    1.77
    鵑
    1.72
    ymce
    1.64
    ष्णा
    1.64
    IMUM
    1.61
     heap
    1.61
     लिखित
    1.57
     Beasley
    1.54
    terase
    1.53
    nię
    1.53
    POSITIVE LOGITS
    uating
    1.79
    brite
    1.63
    uality
    1.61
    i
    1.48
    ActionEvent
    1.46
    l
    1.32
    tend
    1.32
    u
    1.32
    uates
    1.30
     taki
    1.30
    Activations Density 0.066%

    No Known Activations