© 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. 139107
    Prev
    Next
    INDEX
    Explanations

    KL divergence calculation

    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
    in
    0.63
    ').':
    0.49
    o
    0.49
     രണ്ടു
    0.46
     distributive
    0.46
     satin
    0.46
     instalments
    0.46
     southern
    0.45
    丂
    0.45
     filme
    0.45
    POSITIVE LOGITS
     التعليم
    0.45
     MANAGEMENT
    0.43
    enswert
    0.43
    غذ
    0.42
    واعد
    0.42
    zyb
    0.41
    خدام
    0.40
    શ્વ
    0.40
    IVE
    0.39
    ريقة
    0.39
    Activations Density 0.004%

    No Known Activations