© 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. 10-GEMMASCOPE-RES-131K
    7. 19734
    Prev
    Next
    INDEX
    Explanations

    words starting with 'AP', 'AM', 'AD', 'AR', 'AS', 'ATT'

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

    This neuron activates on all‐caps letter sequences (uppercase acronyms or names).

    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
    ፨
    -2.81
    𖣔
    -2.70
     ANY
    -2.53
     なら
    -2.48
     Currently
    -2.47
    𓐍
    -2.41
     Voraussetzung
    -2.36
    になりますが
    -2.33
    でしたが
    -2.31
    Ꭸ
    -2.31
    POSITIVE LOGITS
    '
    3.56
    {
    2.81
    勠
    2.72
    捯
    2.69
    S
    2.58
    ON
    2.53
    P
    2.52
    B
    2.44
    AN
    2.34
     стоковая
    2.33
    Activations Density 0.078%

    No Known Activations