© 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. 113150
    Prev
    Next
    INDEX
    Explanations

    list items with asterisks

    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
    cję
    0.58
    წერ
    0.57
    robespierre
    0.50
    ὴν
    0.48
    pubescens
    0.48
    mensagem
    0.48
    <unused28>
    0.47
    saldo
    0.47
    möglich
    0.47
    señ
    0.46
    POSITIVE LOGITS
    大
    0.51
    用
    0.49
    会
    0.49
    将
    0.49
    با
    0.48
    の
    0.48
    在
    0.48
     Diaries
    0.47
    高
    0.47
    无
    0.47
    Activations Density 0.000%

    No Known Activations