© 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. 102845
    Prev
    Next
    INDEX
    Explanations

    protected, private, include, super

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

    This neuron responds to long runs of space characters (indentation in code or markup).

    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
    //
    -1.54
    );//
    -1.42
     //
    -1.38
    ();//
    -1.33
    ;//
    -1.23
     {//
    -1.21
    /**
    -1.17
    )//
    -1.17
    ,//
    -1.14
    ];//
    -1.13
    POSITIVE LOGITS
     this
    1.39
     these
    1.13
     such
    1.05
     those
    1.03
    int
    1.00
     isn
    0.98
     int
    0.98
     doesn
    0.95
    this
    0.94
    toxicity
    0.86
    Activations Density 0.001%

    No Known Activations