© 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. 4061
    Prev
    Next
    INDEX
    Explanations

    media reviews and critics

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

    The neuron activates strongly on newspaper‐style review headings and bylines—i.e. the section title (“FILM REVIEW”), “By” lines, publication dates, and other review‐article metadata.

    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
    واره
    -0.90
     retailer
    -0.81
    analysis
    -0.76
     Analysis
    -0.75
     Mayor
    -0.73
     editorial
    -0.73
    Letter
    -0.72
     marketer
    -0.71
    жаю
    -0.70
     studies
    -0.69
    POSITIVE LOGITS
     critic
    1.07
     recensione
    0.88
     Critic
    0.87
     critics
    0.82
     крити
    0.81
     favourably
    0.80
     críticos
    0.80
    critic
    0.80
    Critic
    0.79
     OND
    0.76
    Activations Density 0.025%

    No Known Activations