© 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. 109087
    Prev
    Next
    INDEX
    Explanations

    Agence France-Presse

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

    The neuron fires on news‐article metadata tokens (numbers, AFP and other agency codes, dateline/location markers, 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_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
    ]='
    -0.84
    displaymath
    -0.82
    checkNotNull
    -0.80
    mere
    -0.79
     (!
    -0.76
    FontWeight
    -0.76
    த
    -0.75
    ously
    -0.75
    *}{
    -0.74
    ladiator
    -0.74
    POSITIVE LOGITS
    Agence
    0.87
    ればいい
    0.81
    arkiv
    0.81
     gevolg
    0.79
    —(
    0.78
    AFP
    0.77
     Messaging
    0.76
    Sui
    0.72
     afbeelding
    0.71
     Ursprung
    0.71
    Activations Density 0.025%

    No Known Activations