© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1721
    Prev
    Next
    INDEX
    Explanations

    therapists

    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_17_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
     Hopefully
    1.60
    ب
    1.60
     IllegalArgument
    1.26
    ق
    1.21
     Technically
    1.19
    Hopefully
    1.18
     Surely
    1.18
     hopefully
    1.16
    د
    1.16
     Theoretically
    1.14
    POSITIVE LOGITS
    tetrahydro
    1.08
     потреби
    1.07
     hurting
    1.04
     přes
    0.99
     gestalt
    0.98
     jeans
    0.98
    œil
    0.97
     сега
    0.97
    lač
    0.96
     tiers
    0.96
    Activations Density 1.536%

    No Known Activations