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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1356
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying descriptions

    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_17_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
    peut
    0.48
     cravings
    0.48
     hark
    0.47
     அளவிற்கு
    0.47
    ल
    0.47
     breakthroughs
    0.47
     scarcity
    0.46
     irrevers
    0.45
     treffen
    0.45
    itive
    0.45
    POSITIVE LOGITS
     behaved
    0.58
    esian
    0.58
     regarded
    0.57
     administered
    0.57
     produced
    0.56
    regarded
    0.56
    oing
    0.54
    yyyyyyyy
    0.53
     consulted
    0.53
    𝖓
    0.53
    Activations Density 0.381%

    No Known Activations