© 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. 72847
    Prev
    Next
    INDEX
    Explanations

    questions with 'how to'

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

    The neuron is triggered by numeric references—digits, numeric section headings, dates or measurements.

    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
     pfalz
    -1.42
    ÈNE
    -1.30
    råd
    -1.27
     absolut
    -1.24
     aficionados
    -1.23
    ◼
    -1.23
    ⓐ
    -1.23
     jedis
    -1.22
     direkte
    -1.21
    čila
    -1.20
    POSITIVE LOGITS
     because
    1.87
     their
    1.75
     they
    1.70
     since
    1.63
     compared
    1.59
     used
    1.53
     only
    1.46
     uses
    1.45
     show
    1.41
     like
    1.39
    Activations Density 0.005%

    No Known Activations