© 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. 35718
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics and limits

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

    The neuron detects technical terms that denote quantitative performance metrics or measured values (e.g., loss, efficiency, deficit, voltage, limit).

    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
     flera
    -1.16
    roides
    -1.11
     femmin
    -1.06
    /***
    -1.04
    -1.02
     dessen
    -0.99
    含有
    -0.98
    atoon
    -0.98
     Kardinal
    -0.98
     myriad
    -0.97
    POSITIVE LOGITS
     this
    1.52
     when
    1.44
     each
    1.43
     before
    1.31
     after
    1.27
    belline
    1.26
     for
    1.15
     while
    1.11
    sprach
    1.06
     on
    1.05
    Activations Density 0.066%
    No Known Activations