© 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. 20788
    Prev
    Next
    INDEX
    Explanations

    married female partners

    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
    朲
    0.41
     ее
    0.40
     pesto
    0.39
     ей
    0.39
     filosóf
    0.38
    ソル
    0.38
     philosophical
    0.37
     ohmic
    0.36
     htonl
    0.36
    Ⴉ
    0.36
    POSITIVE LOGITS
     wives
    1.13
     wife
    1.09
     ഭാര്യ
    1.07
     female
    1.03
     women
    1.01
    妻子
    1.01
    wife
    1.00
     पत्नी
    1.00
     여성
    1.00
     females
    0.99
    Activations Density 0.292%

    No Known Activations