© 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. 107753
    Prev
    Next
    INDEX
    Explanations

    code snippets and problem descriptions

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

    The neuron is signaling on proper‐name or technical‐reference tokens—e.g. organization or journal titles, domain names/URLs, command‐line flags—i.e. named entities or other “techey” tokens.

    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
    Rispondi
    -0.75
     drawing
    -0.73
     presença
    -0.68
    ому
    -0.67
    יג
    -0.67
     responds
    -0.67
     retailing
    -0.65
    udades
    -0.64
    ்க
    -0.63
     replay
    -0.63
    POSITIVE LOGITS
     Jay
    0.74
    UKU
    0.73
     keratin
    0.73
     Cristiano
    0.73
    ğa
    0.72
    Senator
    0.71
     dolar
    0.71
    cytes
    0.71
     Maire
    0.69
    🪳
    0.69
    Activations Density 0.039%

    No Known Activations