© 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. 116003
    Prev
    Next
    INDEX
    Explanations

    determiners and quantifiers

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

    The neuron activates on self- or biographical narrative statements (e.g. personal background, experiences, or life details).

    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
    🫓
    -1.33
    ℣
    -1.21
     dunque
    -1.16
     instagram
    -1.15
     embodying
    -1.13
    Autocomplete
    -1.12
     TikTok
    -1.09
     contexts
    -1.08
    dillas
    -1.08
    ccional
    -1.07
    POSITIVE LOGITS
     varias
    1.03
    所谓的
    1.03
     unbelievable
    1.03
     several
    0.98
    又は
    0.98
    modus
    0.96
     indicó
    0.96
     Хотя
    0.95
    いろいろな
    0.94
     denominado
    0.94
    Activations Density 0.229%

    No Known Activations