© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13601
    Prev
    Next
    INDEX
    Explanations

    Google Docs, orbital spacecraft, legal rocketry

    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_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
     unsurprisingly
    0.56
     LaTeX
    0.48
     ‌
    0.46
    一会儿
    0.45
    <unused2173>
    0.45
    <unused2130>
    0.43
     HttpException
    0.42
     metadata
    0.42
     practitioner
    0.42
     отмечает
    0.42
    POSITIVE LOGITS
    壹百
    0.66
     monies
    0.65
     yrs
    0.64
     Govt
    0.63
    刋
    0.63
     ALL
    0.63
     Hwy
    0.62
    埸
    0.62
     부터
    0.61
     aprox
    0.61
    Activations Density 0.051%

    No Known Activations