© 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. 22-GEMMASCOPE-RES-131K
    7. 104217
    Prev
    Next
    INDEX
    Explanations

    numerical figures and quantities

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

    This neuron doesn’t respond to any of the shown text—it remains silent on all these excerpts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Although
    -1.14
    Variante
    -1.11
    While
    -1.05
     pinturas
    -1.04
    Both
    -1.01
    These
    -0.94
     Although
    -0.93
    Though
    -0.92
    Only
    -0.91
     mulia
    -0.91
    POSITIVE LOGITS
     superseded
    0.88
     niekoľ
    0.86
    providedIn
    0.85
    siune
    0.80
    ôts
    0.77
    BeNil
    0.76
    出于
    0.75
     להשת
    0.75
    ळ
    0.74
     Currency
    0.74
    Activations Density 0.128%

    No Known Activations