© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1608
    Prev
    Next
    INDEX
    Explanations

    X-related

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

    The neuron flags the leading subword piece of longer words (i.e. the initial BPE token in multi‐piece content 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
     assortment
    -1.24
    krivelse
    -1.08
    与此同时
    -1.05
    ’
    -1.04
    除此之外
    -1.03
    熠
    -1.02
    ebly
    -1.02
    졌
    -1.00
    oczes
    -0.99
     proposal
    -0.97
    POSITIVE LOGITS
     related
    1.70
    related
    1.41
     based
    1.07
     liés
    1.05
    Related
    1.03
     Related
    1.03
     précédentes
    1.02
    type
    1.02
     its
    0.95
     ilgili
    0.93
    Activations Density 0.225%

    No Known Activations