© 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. 10-GEMMASCOPE-RES-131K
    4. 104835
    Prev
    Next
    INDEX
    Explanations

    ratio of radii or distances

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

    The neuron fires on numerals and numeric expressions (e.g. measurements, constants, variable subscripts) in scientific 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
     where
    -1.53
     which
    -1.45
     Direito
    -1.38
     how
    -1.38
     with
    -1.26
     Präsidenten
    -1.17
     ambao
    -1.17
     not
    -1.17
     a
    -1.16
    pantal
    -1.15
    POSITIVE LOGITS
    쟈
    1.39
     если
    1.35
     إضافة
    1.30
     secundarios
    1.27
     actuelles
    1.27
    xically
    1.23
    leggio
    1.21
    рис
    1.20
    jugador
    1.19
    '");
    1.18
    Activations Density 0.063%

    No Known Activations