© 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. 1835
    Prev
    Next
    INDEX
    Explanations

    identifying an entity description

    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
    时
    0.46
     corresponds
    0.46
     είναι
    0.45
     comprise
    0.45
     时
    0.45
     queued
    0.44
     comprises
    0.44
    Response
    0.43
     comprised
    0.43
     는
    0.43
    POSITIVE LOGITS
     Australian
    0.52
     Zimbabwean
    0.52
     Pakistani
    0.51
     Ав
    0.47
    Australian
    0.45
     prominent
    0.45
     Emirati
    0.45
     American
    0.45
     پاکستانی
    0.43
     Cambodian
    0.43
    Activations Density 0.023%

    No Known Activations