© 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. 22-GEMMASCOPE-RES-131K
    4. 68509
    Prev
    Next
    INDEX
    Explanations

    for loops

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

    The neuron is primarily detecting numeric literals (digits) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     alkoholu
    -1.27
    anız
    -1.27
    dekat
    -1.24
     participer
    -1.22
    dengan
    -1.21
     especias
    -1.21
     ekolog
    -1.19
    nyata
    -1.19
    Viitteet
    -1.19
     querían
    -1.14
    POSITIVE LOGITS
    l
    1.17
    W
    1.13
    ne
    1.12
     not
    1.10
    ]
    1.09
    }
    1.07
     없
    1.07
     =
    1.06
    _
    1.03
     is
    1.02
    Activations Density 0.001%

    No Known Activations