© 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. 22-GEMMASCOPE-2-RES-65K
    7. 4984
    Prev
    Next
    INDEX
    Explanations

    specific clinical synopsis

    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_65k_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
     surprise
    1.12
     SME
    1.10
    
    1.08
     energ
    1.08
     selles
    1.06
     speedboat
    1.06
     lactate
    1.06
     kilowatt
    1.06
     ounces
    1.05
     Nina
    1.05
    POSITIVE LOGITS
    worn
    1.26
    yama
    1.24
    y
    1.21
    ኙ
    1.08
    maybe
    1.06
    skinned
    1.06
    ra
    1.05
     بد
    1.04
     значение
    1.03
    ivalence
    1.03
    Activations Density 0.000%

    No Known Activations