© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 16396
    Prev
    Next
    INDEX
    Explanations

    herbal tea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     معیار
    0.53
    🔈
    0.49
    棫
    0.48
    髹
    0.48
    🚄
    0.46
    ന്ധി
    0.46
    🔩
    0.45
    㭜
    0.45
    ጷ
    0.45
    📪
    0.45
    POSITIVE LOGITS
     herbal
    0.88
     herbs
    0.85
     medicinal
    0.74
     Herbal
    0.72
     herb
    0.71
     baths
    0.70
     terapia
    0.70
     therapy
    0.70
     Herbs
    0.69
     therapeutic
    0.67
    Activations Density 0.005%

    No Known Activations