© 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. 22-GEMMASCOPE-RES-131K
    7. 28078
    Prev
    Next
    INDEX
    Explanations

    photo credits and notes

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

    The neuron spikes on photo‐caption credit lines and metadata (e.g. “Mandatory Credit,” agency names, “DIGITAL IMAGE,” etc.).

    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
     we
    -1.09
     étanche
    -1.05
    TextChanged
    -1.03
     ваш
    -0.98
     aprend
    -0.98
     your
    -0.97
     anunci
    -0.97
    
    -0.96
     հղումներ
    -0.96
    づくり
    -0.96
    POSITIVE LOGITS
    Ľ
    1.44
     diminta
    1.32
    ⽐
    1.30
    Aantal
    1.27
    ariums
    1.17
    Kamera
    1.15
    !("{}",
    1.14
    irait
    1.14
    anciers
    1.14
     fotografii
    1.13
    Activations Density 0.025%

    No Known Activations