© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99223
    Prev
    Next
    INDEX
    Explanations

    protecting the environment and people

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

    words or phrases related to protection of the environment, rights, or resources.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on different inflected forms of “protect” (e.g. protect, protection, protecting).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     It
    -1.68
    </h2>
    -1.59
    x
    -1.56
    )
    -1.52
    end
    -1.47
     zimní
    -1.42
     some
    -1.39
    ( ̄
    -1.38
     That
    -1.34
     for
    -1.31
    POSITIVE LOGITS
     protection
    1.66
    みを
    1.66
     durch
    1.61
    zí
    1.49
    稍微
    1.48
     экрана
    1.48
    完全に
    1.47
    >();
    
    1.47
    ungalows
    1.47
    镲
    1.46
    Activations Density 0.025%

    No Known Activations