© 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. 10532
    Prev
    Next
    INDEX
    Explanations

    allergic reactions and sensitivities

    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
    顱
    1.09
    棺
    1.03
     boardwalk
    0.99
    legraph
    0.98
    水位
    0.97
    க
    0.96
    strokes
    0.96
    deos
    0.95
    炔
    0.94
    텔
    0.92
    POSITIVE LOGITS
     allergy
    1.89
     allergic
    1.83
     antigens
    1.74
     alerg
    1.72
     Allergy
    1.65
     allergies
    1.63
     anaphyl
    1.63
     allergens
    1.57
     Allerg
    1.53
     allerg
    1.53
    Activations Density 0.157%

    No Known Activations