© 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. 9-GEMMASCOPE-2-RES-16K
    7. 149
    Prev
    Next
    INDEX
    Explanations

    at its core

    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_9_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
     shout
    1.87
    ે
    1.85
    ر
    1.82
    lessly
    1.78
    erar
    1.70
    र
    1.67
    퉁
    1.63
    ात
    1.62
    нием
    1.60
    naires
    1.58
    POSITIVE LOGITS
     least
    2.51
     saka
    2.27
    razine
    2.24
     ease
    1.99
    kinson
    1.89
    ities
    1.88
     grips
    1.87
     forefront
    1.80
    どう
    1.79
     odds
    1.75
    Activations Density 0.315%

    No Known Activations