© 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. 18787
    Prev
    Next
    INDEX
    Explanations

    equations, prime numbers, facts, opinion

    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
     championships
    1.11
     perfumes
    1.07
     menus
    1.07
     extravaganza
    1.06
     dukkham
    1.05
    嚆
    1.05
     droughts
    1.04
     textAlign
    1.04
     alarms
    1.04
     museums
    1.04
    POSITIVE LOGITS
    Ad
    0.90
    Direct
    0.89
    Inform
    0.89
    Mo
    0.88
    Mild
    0.88
    Flash
    0.88
    Advanced
    0.88
    Visual
    0.87
    Proposition
    0.87
    С
    0.87
    Activations Density 0.000%

    No Known Activations