© 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. 13423
    Prev
    Next
    INDEX
    Explanations

    Czech Republic v

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

    The neuron primarily activates on numeric literals (sequences of digits, including integers and decimals) regardless of context.

    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
     gånger
    -1.36
    Kelebihan
    -1.24
    しちゃ
    -1.18
    Zubereitung
    -1.11
     """",
    -1.09
    Tujuan
    -1.07
    しと
    -1.05
    ﾚ
    -1.05
    〜！
    -1.05
     trabalha
    -1.05
    POSITIVE LOGITS
    knitted
    1.16
    為に
    1.12
     meestal
    1.11
    Эзоҳ
    1.09
    ❣️
    1.04
     prachtig
    1.03
    gucci
    1.01
    skid
    1.00
     afbeelding
    1.00
    ための
    1.00
    Activations Density 0.009%

    No Known Activations