© 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. 64829
    Prev
    Next
    INDEX
    Explanations

    technical terms and models

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

    This neuron detects numeric literals (e.g. integers or floats) in code or 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_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
     necessary
    -1.23
     السياس
    -1.22
     doña
    -1.21
    adesivo
    -1.20
     الحكومة
    -1.18
     Enciclopedia
    -1.17
     Kompon
    -1.16
     Scuola
    -1.16
     misst
    -1.15
     located
    -1.14
    POSITIVE LOGITS
     Hinsicht
    1.21
    contoh
    1.12
    Esperamos
    1.10
     bakgrund
    1.07
     möchtest
    1.06
     varandra
    1.06
     республики
    1.05
    BuildConfig
    1.05
     verbessert
    1.05
    不好意思
    1.05
    Activations Density 0.008%

    No Known Activations