© 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. 22-GEMMASCOPE-RES-131K
    7. 75003
    Prev
    Next
    INDEX
    Explanations

    helping, healing, or teaching

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

    The neuron fires strongly on words that appear in headlines or section titles (i.e. the prominent, capitalized words at the start of articles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     poë
    -1.31
    iress
    -1.23
     Selamat
    -1.22
    licopter
    -1.22
    tså
    -1.20
     Kartu
    -1.20
     lemp
    -1.16
    strains
    -1.15
     vinci
    -1.13
     большинстве
    -1.13
    POSITIVE LOGITS
     not
    1.66
     “
    1.45
     both
    1.43
     also
    1.40
     didn
    1.36
    “
    1.20
     "
    1.16
    </h5>
    1.13
     diverse
    1.10
     even
    1.09
    Activations Density 0.089%

    No Known Activations