© 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. 103090
    Prev
    Next
    INDEX
    Explanations

    possessive followed by attribute

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

    The neuron is looking for tokens that are (or contain) numeric digits—that is, numbers or number-like strings.

    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
    Ⓡ
    -1.13
    nels
    -1.11
     when
    -1.09
    hores
    -1.09
    さの
    -1.08
    ttes
    -1.07
    iamo
    -1.07
    ourced
    -1.06
    paedia
    -1.05
    bodied
    -1.04
    POSITIVE LOGITS
     ability
    2.45
     inability
    2.14
     lack
    1.94
     proximity
    1.87
     status
    1.80
     tendency
    1.79
     constant
    1.73
     willingness
    1.69
     similarity
    1.66
     obvious
    1.66
    Activations Density 0.082%

    No Known Activations