© 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. 10-GEMMASCOPE-RES-131K
    7. 39373
    Prev
    Next
    INDEX
    Explanations

    reason for this

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

    This neuron detects cue phrases that introduce or request explanations of causation—e.g. “the reason for… is,” “reasons for…,” and “why is that.”

    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
    quido
    -1.29
    इटम
    -1.24
     Nowadays
    -1.24
    Viitteet
    -1.24
     WITH
    -1.24
    ностях
    -1.23
    icherheit
    -1.23
    沨
    -1.22
     Entsche
    -1.19
    ரா
    -1.17
    POSITIVE LOGITS
     caucho
    1.20
     are
    1.20
    .
    1.13
    czek
    1.13
     особенно
    1.12
     desblo
    1.10
     lavable
    1.09
     conexão
    1.09
     couldn
    1.07
     nuestra
    1.06
    Activations Density 0.037%

    No Known Activations