© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3607
    Prev
    Next
    INDEX
    Explanations

    running and related activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    钣
    0.71
    傀
    0.68
     Toxicity
    0.64
    toxicity
    0.64
    ገል
    0.63
    ত্তির
    0.62
    ∝
    0.62
    ണ്ഡി
    0.61
    adne
    0.60
    𓂀
    0.60
    POSITIVE LOGITS
     runners
    3.36
     running
    3.33
     Running
    3.26
     runner
    3.21
    Running
    3.17
     Runners
    3.08
    running
    3.08
     Runner
    3.01
    Run
    2.98
     run
    2.97
    Activations Density 0.238%

    No Known Activations