© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6166
    Prev
    Next
    INDEX
    Explanations

    launchLaunchAction

    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_22_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
    交往
    0.66
     벌
    0.59
     excurs
    0.57
    itura
    0.57
    Hand
    0.56
     설계
    0.56
     Hon
    0.56
     담
    0.55
    ઈએ
    0.55
     extensão
    0.54
    POSITIVE LOGITS
    LaunchAction
    0.84
    vish
    0.79
    rice
    0.75
     rights
    0.73
     bijective
    0.72
    തെന്നും
    0.71
    ரி
    0.71
     =$
    0.70
    ത്തിന
    0.70
     ইন্টারনেট
    0.69
    Activations Density 0.077%

    No Known Activations