© 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. 5600
    Prev
    Next
    INDEX
    Explanations

    when introducing conditions or processes

    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
    𝙚
    0.68
     لأن
    0.66
     Hinweis
    0.64
    gesetz
    0.64
     चोपड़ा
    0.62
    quela
    0.60
     lahko
    0.59
     నే
    0.59
     بأن
    0.58
    น
    0.58
    POSITIVE LOGITS
    soever
    0.86
    때
    0.81
     encountering
    0.73
    ли
    0.66
    searching
    0.66
    مة
    0.65
    ।
    0.65
     fertil
    0.63
    ី
    0.63
    ту
    0.61
    Activations Density 0.088%

    No Known Activations