© 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. 130961
    Prev
    Next
    INDEX
    Explanations

    off [something]

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

    The neuron specializes in detecting numeric quantities, such as measurements, counts, or other digit‐based values.

    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
    ми
    -1.62
     that
    -1.50
     эту
    -1.48
    喟
    -1.44
     accordance
    -1.38
    
    -1.35
     Donde
    -1.35
    呿
    -1.33
    のおかげ
    -1.33
     brasile
    -1.33
    POSITIVE LOGITS
     off
    1.76
    z
    1.62
     likes
    1.59
    k
    1.53
     feiert
    1.39
    店的
    1.39
     biggest
    1.38
    os
    1.38
     seems
    1.37
     dicono
    1.36
    Activations Density 0.018%

    No Known Activations