© 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. 81628
    Prev
    Next
    INDEX
    Explanations

    Willie Mat

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

    The neuron is selectively firing on non‐function (“content”) words—i.e. informative or “keyword” tokens (nouns/verbs/etc.) rather than common stopwords or punctuation.

    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
     salón
    -0.87
     شارژ
    -0.86
     Feldman
    -0.79
     memp
    -0.79
    érale
    -0.77
     speaker
    -0.77
    ograf
    -0.76
    rabbit
    -0.76
     impresion
    -0.76
     topo
    -0.75
    POSITIVE LOGITS
     iterator
    0.87
    INDOW
    0.81
     คว
    0.78
     abreast
    0.76
     Возможно
    0.75
     释放
    0.74
    XDECREF
    0.74
     Mungkin
    0.74
     possibilidade
    0.73
     入れ
    0.73
    Activations Density 0.000%

    No Known Activations