© 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. 22-GEMMASCOPE-RES-131K
    4. 35691
    Prev
    Next
    INDEX
    Explanations

    From followed by Four

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

    The neuron fires on the “s” in printf‐style format specifiers (e.g. the “%s” placeholders in a String.format call).

    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
     других
    -0.96
    看到
    -0.93
    其他
    -0.92
    好似
    -0.92
     中
    -0.92
    ValueGenerated
    -0.89
     július
    -0.88
    ſſen
    -0.87
    étisme
    -0.86
    entiated
    -0.85
    POSITIVE LOGITS
    Artes
    1.04
    boite
    1.04
    Rojo
    1.01
     murieron
    0.98
    してくれます
    0.98
    posure
    0.96
    kson
    0.96
    íg
    0.95
    classID
    0.94
    Sì
    0.94
    Activations Density 0.000%

    No Known Activations