© 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. 43328
    Prev
    Next
    INDEX
    Explanations

    rapid growth and magnitude

    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
    🤝
    0.44
     específicas
    0.42
    CC
    0.40
    向けの
    0.40
    DS
    0.40
    た
    0.40
    PROVIDER
    0.39
    ୍ର
    0.39
    目の
    0.39
    рам
    0.38
    POSITIVE LOGITS
     szybko
    0.47
     inflatable
    0.44
     rapidly
    0.42
     rapidamente
    0.42
     radiologists
    0.42
    莴
    0.41
     schneller
    0.40
     postoperative
    0.40
     revolution
    0.39
     arthrop
    0.39
    Activations Density 0.009%

    No Known Activations