© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14352
    Prev
    Next
    INDEX
    Explanations

    comfort and comfortables

    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_262k_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
    urrection
    0.75
    駁
    0.63
    ంశ
    0.62
     datasets
    0.62
    제
    0.62
    Dataset
    0.59
     फेड
    0.58
    propagation
    0.58
    冼
    0.57
    aku
    0.57
    POSITIVE LOGITS
     comfort
    4.57
     Comfort
    4.19
    Comfort
    4.15
     comfortable
    4.13
    comfort
    4.06
     Comfortable
    3.90
     комфор
    3.79
    comfortable
    3.70
    舒适
    3.68
     confort
    3.65
    Activations Density 0.183%

    No Known Activations