© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34773
    Prev
    Next
    INDEX
    Explanations

    referring to prior information

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

    The neuron detects in-text cross‐reference cues (words like “above,” “before,” “mentioned,” etc.) that point to other parts of the document.

    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
    cakup
    -1.13
     zaterdag
    -1.07
    UIFont
    -1.05
     onderstaande
    -1.04
     at
    -1.02
    zapatilla
    -1.01
     each
    -0.98
    ubereitung
    -0.97
     from
    -0.97
     surpassed
    -0.97
    POSITIVE LOGITS
    一惊
    1.03
     cordes
    0.99
    ftar
    0.97
    unto
    0.97
    needs
    0.95
     contextLoads
    0.95
     twenties
    0.95
     大きい
    0.95
    手里的
    0.94
     réglable
    0.93
    Activations Density 0.013%

    No Known Activations