© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11646
    Prev
    Next
    INDEX
    Explanations

    excel file or a unit like kilograms

    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_13_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
    SMS
    1.19
     ineffective
    1.19
     overcrowding
    1.18
    startY
    1.15
     naïve
    1.14
     abundantly
    1.11
    тся
    1.10
    ى
    1.10
    Central
    1.08
    fetched
    1.07
    POSITIVE LOGITS
    li
    1.23
     Service
    1.08
     Granted
    1.07
    lı
    1.04
     Bowls
    1.01
    nega
    1.01
    ্ম্ম
    1.01
     الحرب
    1.01
     فوجی
    0.99
    cı
    0.97
    Activations Density 0.004%

    No Known Activations