© 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. 10-GEMMASCOPE-RES-131K
    7. 99902
    Prev
    Next
    INDEX
    Explanations

    accumulate, accumulation, accumbens

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

    The neuron detects forms of the word "accumulate" and related biochemical terms like "umb/ens" (accumbens) in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the stem “accum” (as in accumulate, accumulation, accumulating, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     quintessential
    -2.52
    那我
    -2.45
     它
    -2.39
    "> 
    -2.38
    ⚊
    -2.25
    
    -2.22
     unending
    -2.19
    鹋
    -2.17
     alluring
    -2.16
     wacky
    -2.11
    POSITIVE LOGITS
    there
    2.34
    the
    2.34
    ),
    2.19
     allow
    2.14
    with
    1.82
     potencial
    1.79
     andar
    1.77
     increíble
    1.72
     an
    1.71
     Not
    1.65
    Activations Density 0.008%

    No Known Activations