© 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. 34-GEMMASCOPE-RES-131K
    4. 75595
    Prev
    Next
    INDEX
    Explanations

    SK Federation

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

    The neuron fires on short all-caps letter sequences (acronyms or two-letter uppercase codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ★★★★
    -0.82
    Chile
    -0.75
    💅
    -0.74
     chick
    -0.73
    VILLA
    -0.73
     snail
    -0.72
    ɔ
    -0.72
    ★★★
    -0.72
    ótica
    -0.69
     Arend
    -0.69
    POSITIVE LOGITS
     Nevis
    1.29
     SK
    1.21
     Basse
    1.07
    SK
    0.95
     Schuhe
    0.88
    🇰
    0.84
    すじ
    0.84
     Bộ
    0.82
     Federation
    0.80
    feder
    0.76
    Activations Density 0.012%

    No Known Activations