© 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. 31831
    Prev
    Next
    INDEX
    Explanations

    presence in

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

    The neuron strongly activates on longer, multisyllabic content words (often technical or domain‐specific terms).

    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
     zaradi
    -1.81
     cálido
    -1.80
     cómodo
    -1.78
     ventilación
    -1.73
     compresión
    -1.69
     überprüft
    -1.66
     bewertet
    -1.66
     soldadura
    -1.65
     flexibilidad
    -1.65
     hormigón
    -1.65
    POSITIVE LOGITS
     in
    10.63
     في
    3.30
    ใน
    3.16
     във
    2.86
     στην
    2.44
     در
    2.42
     dalam
    2.36
     katika
    2.27
     în
    2.13
     dans
    2.11
    Activations Density 2.571%

    No Known Activations