© 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. 26326
    Prev
    Next
    INDEX
    Explanations

    qualities, outcomes, and strategies

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

    The neuron fires on abstract corporate or marketing buzzwords expressing values, qualities, commitments, and action–oriented nouns.

    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
     but
    -1.77
     различни
    -1.38
     as
    -1.34
     Automó
    -1.34
     motivadoras
    -1.33
     artísticas
    -1.29
     históricas
    -1.27
     participado
    -1.24
     obrázok
    -1.23
     or
    -1.22
    POSITIVE LOGITS
     enquanto
    1.16
    .”
    1.10
     AppColors
    1.09
     hecta
    1.08
     across
    1.00
    </b>
    1.00
    deficient
    1.00
    endphp
    0.98
     frequentemente
    0.98
    </em>
    0.97
    Activations Density 0.097%

    No Known Activations