© 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. 10993
    Prev
    Next
    INDEX
    Explanations

    unethical or harmful 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_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
    ž
    0.62
    ان
    0.61
    u
    0.61
    an
    0.61
    已
    0.60
    સ
    0.60
    л
    0.58
    一个
    0.57
    н
    0.57
    iin
    0.57
    POSITIVE LOGITS
     develops
    0.75
     defines
    0.75
     optimizes
    0.74
     Builds
    0.73
     determines
    0.72
     allevi
    0.71
     builds
    0.71
     inherits
    0.71
     brings
    0.70
     improves
    0.70
    Activations Density 0.472%

    No Known Activations