© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127179
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or quotes

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

    The neuron chiefly picks out standalone numeric values (especially decimals and other numbers).

    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
    ſch
    -1.74
    戗
    -1.70
    lossing
    -1.68
     perfectos
    -1.63
     kontrol
    -1.63
    XXXXX
    -1.60
    bör
    -1.59
     帅气
    -1.59
     abonnement
    -1.58
     evenement
    -1.58
    POSITIVE LOGITS
    2
    2.39
    or
    2.33
    but
    2.22
    y
    2.22
    v
    2.20
    This
    2.13
    m
    2.09
    d
    2.08
    w
    2.03
    j
    2.02
    Activations Density 0.040%

    No Known Activations