© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    pollination and pollinators

    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
    崭
    0.45
    晫
    0.42
     명령어
    0.41
    뉴
    0.41
    Hockey
    0.40
    คองโก
    0.40
    кета
    0.40
    িকো
    0.39
     abusive
    0.39
    驹
    0.39
    POSITIVE LOGITS
     pollin
    2.64
     pollen
    2.63
     pollination
    2.61
     Poll
    2.30
     pollinators
    2.28
    poll
    2.16
     poll
    2.05
    Poll
    2.02
     POLL
    1.86
     polls
    1.46
    Activations Density 0.017%

    No Known Activations