© 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-262K
    7. 9021
    Prev
    Next
    INDEX
    Explanations

    JoinColumn Column Padding

    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_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
    粲
    1.43
     classy
    1.39
    т
    1.28
     empiezan
    1.26
    istocene
    1.26
    
    1.23
    広い
    1.23
     speaking
    1.21
     pals
    1.21
    στή
    1.20
    POSITIVE LOGITS
    r
    1.11
    box
    1.02
    f
    1.00
    фин
    0.99
     distint
    0.98
    lle
    0.98
    воре
    0.97
    ди
    0.97
    rai
    0.97
    fins
    0.97
    Activations Density 0.000%

    No Known Activations