© 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. 22-GEMMASCOPE-RES-131K
    7. 64682
    Prev
    Next
    INDEX
    Explanations

    making a difference in lives

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

    The neuron activates on words and phrases that denote making an impact or difference (e.g. “difference,” “impact,” “change,” “effect”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.34
     recherches
    -1.14
     plenamente
    -1.11
    isatie
    -1.08
     tutte
    -1.07
    جميع
    -1.05
     ampliamente
    -1.03
    zunehmen
    -1.02
     всички
    -1.01
     procedentes
    -0.99
    POSITIVE LOGITS
     people
    1.52
     lives
    1.36
     impact
    1.35
     by
    1.29
     in
    1.23
    \}$
    1.22
     didn
    1.20
     благодаря
    1.12
    </em>
    1.12
     Impact
    1.08
    Activations Density 0.018%

    No Known Activations