© 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. 108126
    Prev
    Next
    INDEX
    Explanations

    groups or populations

    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
    z
    0.53
    k
    0.52
    dasarkan
    0.49
    input
    0.47
    mat
    0.47
    itched
    0.47
    b
    0.47
    崎
    0.46
     {
    0.45
    src
    0.45
    POSITIVE LOGITS
     Анг
    0.54
     ইংল্যান্ড
    0.49
     Tesco
    0.49
     групп
    0.47
     tradu
    0.46
    返品
    0.46
     franchises
    0.44
    ʸ
    0.43
     इंग्लैंड
    0.43
     Heinz
    0.43
    Activations Density 0.003%

    No Known Activations