© 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. 82736
    Prev
    Next
    INDEX
    Explanations

    problems highlighted

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

    The neuron is a strong detector of formal, academic/scientific prose—i.e. tokens from research‐article body text.

    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
     нужно
    -1.19
     microbiome
    -1.17
    https
    -1.15
     impactful
    -1.11
     playbook
    -1.09
     Covid
    -1.05
    части
    -1.05
     incentiv
    -1.03
     effectu
    -1.03
     folks
    -1.02
    POSITIVE LOGITS
     particularly
    1.27
    Ironically
    1.18
     problems
    1.15
     highlighted
    1.12
     areas
    1.11
     alerted
    1.08
     detectar
    1.04
    Посилання
    1.03
     difficulties
    1.02
    Surprisingly
    1.02
    Activations Density 0.108%

    No Known Activations