© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38395
    Prev
    Next
    INDEX
    Explanations

    questioning or listing facts

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

    The neuron fires strongly on snake_case option names and other code‐style configuration parameters (e.g. “gather_facts: no”).

    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
     berita
    -0.83
    வெ
    -0.81
    ionali
    -0.77
     torneo
    -0.77
     some
    -0.77
    Ұ
    -0.76
     gagal
    -0.75
     région
    -0.74
    Ł
    -0.74
     Mondiale
    -0.73
    POSITIVE LOGITS
     intertw
    0.86
     médié
    0.80
     embellished
    0.80
    Useless
    0.79
    Faults
    0.79
     buoyancy
    0.78
    probe
    0.77
     يكن
    0.76
    Complaint
    0.76
    ző
    0.74
    Activations Density 0.006%

    No Known Activations