© 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. 42710
    Prev
    Next
    INDEX
    Explanations

    particular order or topic

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

    The neuron specifically detects occurrences of the word “particular.”

    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
     interessantes
    -1.39
    穽
    -1.38
    𓁹
    -1.38
     servido
    -1.38
     requisite
    -1.36
    зывают
    -1.35
    ]
    -1.34
     quintessential
    -1.34
    itisation
    -1.33
    RODU
    -1.30
    POSITIVE LOGITS
    5
    1.51
     or
    1.48
    6
    1.32
     banan
    1.23
    8
    1.21
     before
    1.20
    4
    1.18
     aiming
    1.16
     also
    1.15
    3
    1.15
    Activations Density 0.045%

    No Known Activations