© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4211
    Prev
    Next
    INDEX
    Explanations

    presents / present / come / brings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    esk
    0.76
    햄
    0.75
    损害
    0.73
     prefers
    0.72
     disadvantage
    0.72
    獎
    0.71
     favours
    0.71
    好处
    0.70
     mislead
    0.70
    奬
    0.69
    POSITIVE LOGITS
     presenting
    0.88
     come
    0.87
     present
    0.86
     comes
    0.86
     presents
    0.85
     Present
    0.80
    present
    0.78
     brings
    0.77
    Bring
    0.77
     Bring
    0.76
    Activations Density 0.405%

    No Known Activations