© 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. 75475
    Prev
    Next
    INDEX
    Explanations

    related to evolutionary departure

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

    race as a social construct, not biological

    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
    ర
    0.49
    ס
    0.48
     ():
    0.47
     первым
    0.46
    
    0.46
    Executable
    0.45
    Allister
    0.44
     পছন্দ
    0.43
    ౖ
    0.43
    ixas
    0.43
    POSITIVE LOGITS
     zwar
    0.50
     temporally
    0.44
     ebenfalls
    0.44
     degraded
    0.43
    temporal
    0.43
     ich
    0.42
     chim
    0.42
     stagnant
    0.41
     Wa
    0.41
     tempor
    0.41
    Activations Density 0.003%

    No Known Activations