© 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. 45548
    Prev
    Next
    INDEX
    Explanations

    XML declaration

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

    The neuron flags tokens containing numeric sequences (e.g. version numbers, numeric IDs, ports, and other digit‐filled strings).

    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
     ली
    -0.87
     An
    -0.85
    Iron
    -0.80
     re
    -0.79
     los
    -0.79
     All
    -0.78
     propOrder
    -0.78
    IAM
    -0.77
     While
    -0.77
    Aud
    -0.77
    POSITIVE LOGITS
     edades
    1.09
    clearpage
    0.92
    https
    0.88
     jouets
    0.88
    umenter
    0.86
     https
    0.85
     .
    0.85
     화면
    0.85
    sistance
    0.83
    http
    0.83
    Activations Density 0.003%

    No Known Activations