© 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. 73414
    Prev
    Next
    INDEX
    Explanations

    because of the

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

    the neuron detects numeric expressions (numbers and numerical measurements) in the text.

    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
    </i>
    -1.65
     tantangan
    -1.64
    奬
    -1.55
     at
    -1.53
    of
    -1.53
     perjuangan
    -1.53
     thirteen
    -1.51
     should
    -1.49
    愜
    -1.49
     when
    -1.48
    POSITIVE LOGITS
     möjlighet
    1.70
    </h4>
    1.63
     amplia
    1.60
    larıyla
    1.54
    ctivo
    1.54
    assword
    1.48
     delgado
    1.48
    蒾
    1.47
     flotante
    1.47
    ࿔
    1.46
    Activations Density 0.037%

    No Known Activations