© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79972
    Prev
    Next
    INDEX
    Explanations

    studio albums or projects

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

    The neuron selectively fires on numeric tokens and identifiers—things like grant numbers, years, series labels, album counts, and other standalone number‐like 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_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
     atitude
    -1.07
     wako
    -1.02
     territ
    -1.01
    Diámetro
    -1.01
     cerimonia
    -0.98
     lettera
    -0.98
    Jegy
    -0.98
     副本
    -0.95
     câncer
    -0.95
     tinto
    -0.94
    POSITIVE LOGITS
     arbete
    1.10
     vermag
    1.06
     THOSE
    1.05
    Caprio
    1.03
                      
    1.02
    腩
    1.02
    ):
    1.01
                          
    1.00
     всегда
    0.99
    otesi
    0.99
    Activations Density 0.087%

    No Known Activations