© 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. 90797
    Prev
    Next
    INDEX
    Explanations

    tomorrow morning

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

    This neuron detects formatting/markup tokens (e.g. indentation spaces or the caret used for superscript in equations).

    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
     other
    -1.86
     this
    -1.71
    他にも
    -1.54
    慣れて
    -1.48
     its
    -1.44
     consiguiente
    -1.43
    流石
    -1.39
    ってみました
    -1.38
    あんまり
    -1.34
    それだけ
    -1.33
    POSITIVE LOGITS
    
    1.65
    MAXN
    1.64
    
    1.63
    дите
    1.54
    ]}$
    1.51
     cuando
    1.51
    isait
    1.51
    WHERE
    1.46
    Affirmed
    1.45
    ходе
    1.41
    Activations Density 0.029%

    No Known Activations