© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3982
    Prev
    Next
    INDEX
    Explanations

    test case descriptions

    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_22_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
     si
    0.67
     invisible
    0.66
    <0xE9>
    0.64
     takie
    0.62
     leading
    0.62
     hidden
    0.62
     linear
    0.61
    istic
    0.61
     개
    0.60
     gi
    0.60
    POSITIVE LOGITS
    另外
    0.79
    Commons
    0.78
    Missense
    0.77
    Drum
    0.76
    𝕙
    0.72
    <unused963>
    0.72
     ತಿಳ
    0.72
    Excerpt
    0.72
    Makefile
    0.72
    Standard
    0.71
    Activations Density 0.009%

    No Known Activations