Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 12678
    Prev
    Next
    INDEX
    Explanations

    working with names memory backwards proficiency

    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
    regator
    0.43
    LAY
    0.40
    াতাড়ি
    0.39
     imposible
    0.39
     ஆராய்ச்சி
    0.38
    Curs
    0.38
    䊂
    0.38
    同步
    0.37
    ৃতির
    0.37
     選
    0.37
    POSITIVE LOGITS
     Working
    0.55
    working
    0.53
     working
    0.52
    Working
    0.47
    WORKING
    0.42
     WORKING
    0.42
     рабочего
    0.42
     कामकाजी
    0.40
     рабочей
    0.37
     drafts
    0.36
    Activations Density 0.006%

    No Known Activations