© 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. 10-GEMMASCOPE-RES-131K
    7. 71418
    Prev
    Next
    INDEX
    Explanations

    delta-frequencies

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

    The neuron detects occurrences of the word “delta” used as a technical label (e.g. in mathematical subscripts, delta‐functions, or chemical/parameter names).

    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
     You
    -2.66
     Those
    -2.50
     That
    -2.27
     produite
    -2.23
     This
    -2.14
     Anyone
    -2.14
     However
    -2.09
     Whether
    -2.03
     Such
    -1.98
     Ideally
    -1.95
    POSITIVE LOGITS
    A
    2.50
    2
    2.38
    ,“
    2.36
    “
    2.02
    For
    1.96
    ]
    1.93
    
    1.91
    )
    1.91
    From
    1.91
    他の
    1.90
    Activations Density 0.012%

    No Known Activations