© 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. 10-GEMMASCOPE-RES-131K
    7. 47621
    Prev
    Next
    INDEX
    Explanations

    certain thresholds or limits

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

    This neuron detects references to numeric thresholds––in particular the phrase “a certain threshold” and related threshold‐specifying 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
     zunächst
    -1.41
    useNewUrlParser
    -1.32
     douleur
    -1.30
    #__
    -1.28
    roughly
    -1.27
    Initially
    -1.27
    basically
    -1.26
    淠
    -1.26
    ݯ
    -1.25
    essentially
    -1.23
    POSITIVE LOGITS
     or
    2.45
     these
    1.88
     specified
    1.47
     certain
    1.30
     such
    1.27
     combining
    1.24
     provided
    1.24
    ihnach
    1.19
     enhance
    1.19
     recently
    1.19
    Activations Density 0.266%

    No Known Activations