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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1390
    Prev
    Next
    INDEX
    Explanations

    paying attention

    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_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
     апреля
    1.15
    纫
    1.01
    wine
    0.97
    alous
    0.96
    jego
    0.95
    edged
    0.93
    exclude
    0.92
     bothering
    0.90
    Ց
    0.90
    Repeat
    0.89
    POSITIVE LOGITS
     attention
    1.84
     homage
    1.74
     tribute
    1.42
     dividends
    1.39
     Attention
    1.38
    attention
    1.28
     heed
    1.26
    laşı
    1.24
     attentions
    1.11
    Attention
    1.10
    Activations Density 0.134%

    No Known Activations