© 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-65K
    7. 48881
    Prev
    Next
    INDEX
    Explanations

    often leading to it

    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_65k_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
    öger
    0.44
    ivating
    0.42
    硖
    0.41
    That
    0.41
    стика
    0.41
    tailed
    0.39
    iece
    0.38
    独特的
    0.38
     pioneering
    0.38
    eniendo
    0.38
    POSITIVE LOGITS
     আসলে
    0.46
     खासकर
    0.43
     szczególnie
    0.40
     ដើម្បី
    0.40
     Fernseh
    0.39
     результатом
    0.39
     навіть
    0.39
    癡
    0.39
     bahkan
    0.39
     salons
    0.39
    Activations Density 0.145%

    No Known Activations