© 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. 25932
    Prev
    Next
    INDEX
    Explanations

    derivatives and adaptations

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

    The neuron detects formal, meta-scientific wording typical of research paper abstracts (e.g. “this article has been written,” “catalysts obtained,” “lead compound showed,” etc.).

    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
     указа
    -0.82
    IsOptional
    -0.79
     metres
    -0.78
    ンプ
    -0.77
    irchen
    -0.77
    /$',
    -0.76
    ngOnDestroy
    -0.75
    liš
    -0.75
    pagnole
    -0.75
    gegeven
    -0.75
    POSITIVE LOGITS
     daraus
    1.33
     version
    1.09
     davon
    0.98
     derivative
    0.96
     deriv
    0.94
    それを
    0.94
    はその
    0.92
    copyOf
    0.90
    后的
    0.89
     adaptations
    0.89
    Activations Density 0.109%

    No Known Activations