© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102619
    Prev
    Next
    INDEX
    Explanations

    Image Credit:

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

    The neuron detects image credit attributions (the “Credit:” labels and their associated numbers).

    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
    ⚢
    -1.69
     також
    -1.46
     certainement
    -1.45
    怱
    -1.42
    esticular
    -1.41
     mój
    -1.41
     福袋
    -1.39
    [?]
    -1.38
    ’
    -1.37
    噐
    -1.36
    POSITIVE LOGITS
    ৪
    1.55
     still
    1.51
     duas
    1.42
    ज़
    1.42
    ৄ
    1.40
    </b>
    1.39
     focusing
    1.36
     ten
    1.28
     fifteen
    1.27
     do
    1.26
    Activations Density 0.011%

    No Known Activations