© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149816
    Prev
    Next
    INDEX
    Explanations

    user-shared conversations

    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_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
     evil
    0.66
     არა
    0.62
     Evil
    0.62
    apus
    0.58
    ہر
    0.58
     mew
    0.57
    隶
    0.57
     herm
    0.57
     lact
    0.57
     lame
    0.56
    POSITIVE LOGITS
     fondly
    0.84
    Males
    0.81
     时尚
    0.78
    /:
    0.78
     variously
    0.78
     Festivals
    0.77
     ஆண்கள்
    0.77
    نساء
    0.77
     Downloading
    0.76
    Sometimes
    0.76
    Activations Density 0.004%

    No Known Activations