© 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. 84497
    Prev
    Next
    INDEX
    Explanations

    android ui file names

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

    The neuron fires on numeric literals (digit sequences), i.e. it detects tokens that are 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
    ebly
    -1.36
     Características
    -1.35
     Descripción
    -1.34
     Tienen
    -1.27
     Pueden
    -1.24
     Aún
    -1.23
    <bos>
    -1.23
     Lleva
    -1.23
     Cualquier
    -1.22
     Incluye
    -1.22
    POSITIVE LOGITS
    آموزش
    1.29
     εικό
    1.27
    ところに
    1.26
     Musiker
    1.22
    ฌ
    1.17
    مقاله
    1.16
    مقدمه
    1.16
     very
    1.15
    =="")
    1.14
     difficult
    1.13
    Activations Density 0.001%

    No Known Activations