© 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. 93264
    Prev
    Next
    INDEX
    Explanations

    VERSION, CONFIGURATION, Compiler, Alias, list, define

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

    The neuron detects numeric literals or tokens containing digits (e.g. integer and decimal numbers).

    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
     what
    -1.29
    hidup
    -1.16
    Whats
    -1.05
    produksi
    -1.05
    zigen
    -1.03
    ösung
    -1.02
     его
    -1.02
     its
    -1.02
    hasilkan
    -1.02
    只
    -1.01
    POSITIVE LOGITS
     besonderes
    1.20
     Rücksicht
    1.13
     frecuentemente
    1.10
     deoarece
    1.08
     ciertos
    1.06
     cuyo
    1.05
     determinados
    1.04
    噤
    1.04
     dichas
    1.04
     cuyos
    1.04
    Activations Density 0.005%

    No Known Activations