© 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. 70998
    Prev
    Next
    INDEX
    Explanations

    introduces enumeration of reasons

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

    The neuron fires on occurrences of the word “reasons,” marking statements that introduce or enumerate reasons.

    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
     â
    -1.84
    🪅
    -1.69
    只见
    -1.64
    cesta
    -1.63
    sapato
    -1.60
     气
    -1.57
    orice
    -1.56
    ])/
    -1.56
     visionary
    -1.55
     the
    -1.54
    POSITIVE LOGITS
    1
    2.58
    2
    2.58
    3
    2.53
    8
    2.33
    7
    2.30
    6
    2.27
    4
    2.22
    0
    2.09
    5
    2.06
    ,
    1.85
    Activations Density 0.010%

    No Known Activations