© 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. 34-GEMMASCOPE-RES-131K
    7. 86936
    Prev
    Next
    INDEX
    Explanations

    cartoon violence, copyright, introduction

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

    The neuron strongly activates on very common, high‐frequency tokens (i.e. “stop words”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     well
    -0.85
     continual
    -0.84
     from
    -0.83
     but
    -0.79
    grandmother
    -0.78
     long
    -0.78
    九年
    -0.78
    }:${
    -0.77
     became
    -0.77
     at
    -0.77
    POSITIVE LOGITS
     [''],
    0.94
    Apparel
    0.92
     artefacts
    0.91
    Artifacts
    0.88
     pite
    0.84
    ceptable
    0.83
     BOY
    0.82
     คา
    0.81
    有多少
    0.81
    わりに
    0.80
    Activations Density 0.002%

    No Known Activations