© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11702
    Prev
    Next
    INDEX
    Explanations

    social justice, belief, stroke, DSL

    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_9_width_262k_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
    𝗔
    0.94
    同比增长
    0.89
     மிசோ
    0.88
    𝗗
    0.85
     êtes
    0.84
    )")
    0.84
     offrant
    0.83
     불구하고
    0.83
     பங்கே
    0.82
    하지
    0.82
    POSITIVE LOGITS
     ひ
    0.81
     either
    0.80
     tutta
    0.79
    み
    0.78
    ط
    0.77
     cominci
    0.77
     একটা
    0.77
    チック
    0.77
    appara
    0.76
    ץ
    0.75
    Activations Density 0.177%

    No Known Activations