© 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. 10-GEMMASCOPE-RES-131K
    4. 42028
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron detects four-digit year numbers (e.g., “1999,” “2001,” “2003”) typically used in copyright or date stamps.

    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
    就没有
    -1.28
    边的
    -1.25
     propietarios
    -1.21
    当然是
    -1.20
    よる
    -1.19
    assem
    -1.16
    没问题
    -1.15
     coreana
    -1.14
     jejich
    -1.13
     Their
    -1.12
    POSITIVE LOGITS
     to
    1.25
    翠
    1.23
    ↵↵↵
    1.17
    mathrm
    1.15
     ammonia
    1.10
    徘
    1.05
     stof
    1.05
    klere
    1.05
     besonder
    1.03
    Specifies
    1.02
    Activations Density 0.288%

    No Known Activations