© 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. 18995
    Prev
    Next
    INDEX
    Explanations

    FAT, font, Width, package

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

    This neuron activates on font-related identifiers (e.g., tokens containing “font”).

    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
    isation
    -1.47
    xelles
    -1.47
     tématu
    -1.45
    }=\
    -1.38
    AMIENTO
    -1.38
    ześnie
    -1.38
    ༀ
    -1.36
     společnost
    -1.32
    cửa
    -1.32
    ilities
    -1.31
    POSITIVE LOGITS
     Futsal
    1.38
     those
    1.36
     conquête
    1.32
    nitř
    1.30
     Philosopher
    1.30
     However
    1.29
    ちゃんは
    1.25
    </b>
    1.25
     poursuite
    1.25
     Despite
    1.23
    Activations Density 0.003%

    No Known Activations