© 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-16K
    7. 10347
    Prev
    Next
    INDEX
    Explanations

    snacks and drinks

    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
     vacations
    0.79
     cooking
    0.71
     clothes
    0.70
     ponds
    0.69
    춧
    0.67
     cooks
    0.66
     domes
    0.65
     cook
    0.64
     Cooking
    0.63
     MCS
    0.63
    POSITIVE LOGITS
     Snack
    1.49
     snack
    1.47
     snacks
    1.41
     Snacks
    1.40
    snacks
    1.38
     snacking
    1.38
     nib
    1.09
     drink
    1.05
    🥨
    1.02
     Chew
    1.02
    Activations Density 0.234%

    No Known Activations