© 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. 10-GEMMASCOPE-RES-131K
    7. 71528
    Prev
    Next
    INDEX
    Explanations

    evolution of features

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

    The neuron detects words and phrases related to "evolution" and changes occurring over time, particularly in scientific contexts.

    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_10/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
    StringVar
    -1.70
    ;
    -1.63
    )
    -1.59
    }
    -1.59
    ("/:
    -1.52
    岨
    -1.50
    ඈ
    -1.48
    ヌーピー
    -1.48
     vetores
    -1.45
     båda
    -1.45
    POSITIVE LOGITS
     on
    1.87
     through
    1.58
     during
    1.54
     some
    1.47
     throughout
    1.30
     in
    1.27
     function
    1.25
     trends
    1.21
     there
    1.13
     had
    1.13
    Activations Density 0.069%

    No Known Activations