© 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. 31-GEMMASCOPE-2-RES-262K
    4. 32798
    Prev
    Next
    INDEX
    Explanations

    alternatives or", "

    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_31_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
    特殊的
    0.43
    một
    0.41
    格外
    0.41
    㡚
    0.41
    ALD
    0.41
    NELL
    0.41
    身的
    0.41
    啶
    0.40
    橑
    0.40
    মন্ত্রীর
    0.40
    POSITIVE LOGITS
     jotka
    0.51
     veya
    0.48
     yoki
    0.47
    errors
    0.46
     nebo
    0.46
     dnes
    0.45
    erny
    0.45
     darunter
    0.44
     oppure
    0.43
    rak
    0.43
    Activations Density 0.001%

    No Known Activations