© 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-262K
    7. 2592
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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
     gesamten
    1.12
     liens
    1.12
     loadImage
    1.11
    Características
    1.02
     уси
    0.99
     kivy
    0.99
    ꞌ
    0.99
     Topic
    0.99
     Trabaj
    0.98
    */
    0.97
    POSITIVE LOGITS
    ishing
    1.09
     combat
    1.07
    न्छ
    1.06
    യ്
    1.05
    ণ
    1.03
     succession
    1.02
    elder
    0.99
    ishment
    0.97
    ection
    0.97
    𝓁
    0.94
    Activations Density 0.000%

    No Known Activations