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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1097
    Prev
    Next
    INDEX
    Explanations

    complement, meaning, or refrigerant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    𒌍
    1.50
     రిడిల్
    1.48
    Cleaning
    1.41
     क़ुर्आन
    1.40
    
    1.39
     वजीरएक्स
    1.38
    <unused1308>
    1.38
    <unused55>
    1.37
    
    1.36
     রাদে
    1.35
    POSITIVE LOGITS
     a
    1.30
     an
    1.24
     ins
    1.04
     it
    1.04
     (
    1.03
    （
    1.02
     for
    1.00
     fundamental
    1.00
     in
    0.97
     as
    0.96
    Activations Density 0.000%

    No Known Activations