© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66712
    Prev
    Next
    INDEX
    Explanations

    academic symbols and code

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

    This neuron detects numeric literals (tokens made up of digits, including integers and floats).

    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
     masculinos
    -1.26
    ﻻ
    -1.13
     souple
    -1.13
     fotográfico
    -1.10
    ￬
    -1.09
     turístico
    -1.09
     jurídico
    -1.06
     čtyř
    -1.05
     mengirimkan
    -1.04
    akujem
    -1.04
    POSITIVE LOGITS
     vanta
    1.09
    ついて
    1.06
     pembelajaran
    1.03
     bluse
    0.97
     diamante
    0.94
     lapangan
    0.94
     scul
    0.93
     panini
    0.92
     Generale
    0.90
     vagab
    0.89
    Activations Density 0.001%

    No Known Activations