© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93338
    Prev
    Next
    INDEX
    Explanations

    words or punctuation

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

    The neuron lights up on open‐class “content” tokens (nouns, verbs, adjectives, numbers, punctuation)—i.e. the meaningful words—rather than on function words.

    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
     because
    -3.42
    因为
    -2.30
    因為
    -2.19
     since
    -2.17
     karena
    -1.90
     Çünkü
    -1.76
     protože
    -1.71
    because
    -1.66
     поскольку
    -1.66
     as
    -1.63
    POSITIVE LOGITS
     eikä
    1.58
     przecież
    1.44
    therefore
    1.41
    Remember
    1.33
    ですから
    1.30
     sonuç
    1.27
     nogal
    1.27
     shouldn
    1.24
     joten
    1.23
    嘛
    1.21
    Activations Density 0.062%

    No Known Activations