© 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. 26295
    Prev
    Next
    INDEX
    Explanations

    Public Administration loans

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

    The neuron detects definitional language—phrases that introduce or state a concept’s definition (e.g. “is defined as,” “the function of,” etc.).

    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
     carregar
    -1.42
    colato
    -1.38
    ſelf
    -1.34
    ῤ
    -1.34
     JMenuItem
    -1.32
    assies
    -1.30
    ＝＝＝＝
    -1.27
     extrêmement
    -1.26
     północ
    -1.26
     eléctrica
    -1.25
    POSITIVE LOGITS
     their
    1.45
     правительства
    1.35
    研究生
    1.28
    鋲
    1.28
     because
    1.22
     饼
    1.20
     tasted
    1.17
     develop
    1.16
    ziała
    1.16
    教材
    1.16
    Activations Density 0.012%

    No Known Activations