© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43210
    Prev
    Next
    INDEX
    Explanations

    progressive genetic conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    genetic conditions and traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    রের
    0.48
    老人
    0.46
    娠
    0.45
    কের
    0.44
    걀
    0.42
     Oktoberfest
    0.42
    눠
    0.42
    忪
    0.42
    膾
    0.41
    犒
    0.41
    POSITIVE LOGITS
     homozyg
    0.72
     homozygous
    0.71
     phenotype
    0.67
     heterozyg
    0.65
     heterozygous
    0.64
     lysosomes
    0.64
     autosomal
    0.61
     genetic
    0.59
     lifelong
    0.57
     transgene
    0.55
    Activations Density 0.065%

    No Known Activations