© 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. 28549
    Prev
    Next
    INDEX
    Explanations

    speed measurements

    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
    6
    0.34
    3
    0.34
    2
    0.32
    5
    0.32
    4
    0.29
    8
    0.29
    7
    0.28
    <0x0D>
    0.26
    ol
    0.25
    0
    0.25
    POSITIVE LOGITS
    ާއި
    0.29
    شناسی
    0.29
    ့်
    0.28
     داشتن
    0.26
     پری
    0.26
     разнообраз
    0.26
     Britannia
    0.26
     और
    0.26
     και
    0.26
     и
    0.25
    Activations Density 0.057%

    No Known Activations