© 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. 84244
    Prev
    Next
    INDEX
    Explanations

    currency amounts or specific abbreviations

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

    The neuron flags code‐oriented tokens—such as programming operators (e.g. “--”) and markup commands (e.g. “itemize”)—rather than ordinary natural‐language words.

    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
     to
    -2.56
     stemming
    -2.16
     akin
    -2.05
    N
    -2.03
    並沒有
    -1.91
    店内
    -1.90
    でございます
    -1.90
    Like
    -1.90
    縷
    -1.87
    蹌
    -1.87
    POSITIVE LOGITS
    н
    3.20
    噐
    2.81
    --)
    2.52
    к
    2.47
    ?"
    2.39
                    
    2.36
    苼
    2.36
    ꪹ
    2.30
     "
    2.27
    夘
    2.27
    Activations Density 0.000%

    No Known Activations