© 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. 10-GEMMASCOPE-RES-131K
    4. 105842
    Prev
    Next
    INDEX
    Explanations

    abbreviations and beginnings of words

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

    This neuron activates on software or product names (e.g. theme names, plugins, modules, frameworks, and other branded identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -1.56
     diğer
    -1.40
     muchos
    -1.36
     algunos
    -1.33
     tienen
    -1.31
     it
    -1.31
     että
    -1.30
     başka
    -1.28
    夜景
    -1.27
     manchmal
    -1.27
    POSITIVE LOGITS
     essenciais
    1.44
     والب
    1.30
    ค์
    1.30
    Already
    1.27
    Software
    1.26
     any
    1.24
     your
    1.23
    Helping
    1.23
     والف
    1.23
     tuturor
    1.23
    Activations Density 0.027%

    No Known Activations