© 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. 95856
    Prev
    Next
    INDEX
    Explanations

    Sunflat Games, DNA fragmentation

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

    code syntax elements related to programming, particularly in contexts like arrays, functions, and data structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron identifies numeric literals (both integers and decimals) in code or text.

    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
     burbu
    -1.23
    ZAR
    -1.12
     Ministro
    -1.08
    אַ
    -1.07
    Oleg
    -1.06
     josé
    -1.06
    嫱
    -1.06
    щены
    -1.04
    ckie
    -1.03
     espere
    -1.03
    POSITIVE LOGITS
     solution
    1.08
    1.02
    ，
    0.98
     дают
    0.97
     períodos
    0.96
     spiders
    0.95
    üyor
    0.95
     pairs
    0.94
     situation
    0.94
     bzw
    0.94
    Activations Density 0.005%
    No Known Activations