© 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. 104586
    Prev
    Next
    INDEX
    Explanations

    achieved status or ranking

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

    The neuron activates on terms introducing or accompanying numeric data—i.e. words that signal measurements, counts, statistics, or numeric values.

    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
     and
    -1.31
     alip
    -1.14
     instead
    -1.09
     Griechen
    -1.06
    ary
    -1.04
     soste
    -1.01
     it
    -0.98
     ebenfalls
    -0.98
    3
    -0.97
     also
    -0.96
    POSITIVE LOGITS
     stratég
    1.23
     orsz
    1.21
     positifs
    1.18
    éről
    1.16
     Fazit
    1.16
     nélk
    1.14
    两人的
    1.14
     appréci
    1.13
     nécess
    1.12
     kateg
    1.12
    Activations Density 0.117%

    No Known Activations