© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 5947
    Prev
    Next
    INDEX
    Explanations

    mother and father

    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_40_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
    小伙伴
    0.43
    男生
    0.42
    蚂
    0.41
    小朋友
    0.39
    ulg
    0.39
    amilton
    0.39
     MAST
    0.39
    Compute
    0.38
    th
    0.38
    ulnerable
    0.37
    POSITIVE LOGITS
     father
    0.75
    hood
    0.72
    뻘
    0.70
    father
    0.68
    🤱
    0.63
    hetical
    0.63
     Vater
    0.63
     mother
    0.62
    mother
    0.61
     materna
    0.61
    Activations Density 0.022%

    No Known Activations