© 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-262K
    7. 5831
    Prev
    Next
    INDEX
    Explanations

    network traffic, sharing, and calls

    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
    ônio
    0.39
    ،
    0.38
    рін
    0.38
    )،
    0.37
    噔
    0.37
    ᗩ
    0.37
    ємо
    0.36
    abu
    0.36
    歿
    0.36
    ANO
    0.35
    POSITIVE LOGITS
     ia
    0.36
     isinstance
    0.36
     pept
    0.35
     implying
    0.34
     whereupon
    0.34
     metre
    0.33
     td
    0.33
     baile
    0.33
     implies
    0.32
     apart
    0.32
    Activations Density 0.000%

    No Known Activations