© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58641
    Prev
    Next
    INDEX
    Explanations

    exhortations and continuance

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

    This neuron fires on words set off as headings or otherwise given special emphasis (e.g. in a larger/bold font).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     bicicletas
    -0.93
     iniciar
    -0.82
    isEmpty
    -0.81
     berbagi
    -0.81
     uz
    -0.79
    Thông
    -0.78
    вається
    -0.78
    いたい
    -0.77
     Ленин
    -0.77
    zwungen
    -0.75
    POSITIVE LOGITS
     firm
    0.99
     continuance
    0.91
     continue
    0.91
    mrow
    0.90
     continued
    0.89
     stay
    0.88
     continually
    0.85
    のですか
    0.85
     приобрести
    0.83
     firmly
    0.83
    Activations Density 0.009%

    No Known Activations