© 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. 22-GEMMASCOPE-RES-131K
    7. 65033
    Prev
    Next
    INDEX
    Explanations

    Australian disable

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

    The neuron detects numeric literals (numbers) in source 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
    そういえば
    -1.36
    それにしても
    -1.23
     of
    -1.18
    几个人
    -1.14
     informace
    -1.14
    踱
    -1.09
    しかも
    -1.09
     surpris
    -1.06
    кою
    -1.05
    子は
    -1.05
    POSITIVE LOGITS
     beliebt
    1.17
    N
    1.15
     ordentlich
    1.08
     aanzien
    1.05
     ↓
    1.05
     gewiß
    1.03
    B
    1.02
     offensichtlich
    1.01
    </em>
    1.00
     seguenti
    0.98
    Activations Density 0.005%

    No Known Activations