© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 20931
    Prev
    Next
    INDEX
    Explanations

    activation or active

    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
     tds
    0.40
    луб
    0.39
     OUTER
    0.36
     façons
    0.36
    щие
    0.35
    decimals
    0.34
     سزا
    0.34
    🛥
    0.34
     xvi
    0.34
     ವ್ಯ
    0.34
    POSITIVE LOGITS
     enabled
    0.42
     ativa
    0.41
    activated
    0.41
    ihat
    0.41
     সক্রিয়
    0.40
     activated
    0.39
    ierten
    0.38
     deaktiv
    0.38
    aktif
    0.38
     βο
    0.38
    Activations Density 0.000%

    No Known Activations