© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40902
    Prev
    Next
    INDEX
    Explanations

    explaining sexual orientation and gender identity

    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
    the
    0.50
    j
    0.50
    x
    0.47
    ))
    0.46
    a
    0.46
    n
    0.45
    )
    0.45
    is
    0.44
    l
    0.44
    r
    0.44
    POSITIVE LOGITS
     همچنین
    0.48
     setLayout
    0.48
    พัฒ
    0.47
    玴
    0.47
     Ayrıca
    0.46
     பயன்படுத்த
    0.46
     continuamente
    0.46
     завжди
    0.46
     encontrar
    0.46
     zależ
    0.45
    Activations Density 0.001%

    No Known Activations