© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106925
    Prev
    Next
    INDEX
    Explanations

    human evolution and origins

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

    references to ancient human ancestors or early human evolution.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     víctima
    -0.74
     Logistics
    -0.74
    bde
    -0.73
     nuôi
    -0.72
    oku
    -0.71
    (|
    -0.69
     Fold
    -0.68
    天文
    -0.68
    matan
    -0.67
     logistic
    -0.66
    POSITIVE LOGITS
     humankind
    1.25
     paleo
    1.20
     hom
    1.16
    Human
    1.14
     Human
    1.13
     human
    1.13
     humanoid
    1.13
     humanity
    1.11
     Homo
    1.09
     Humanity
    1.07
    Activations Density 0.026%

    No Known Activations